{
  "benchmark_line": "gamebench2",
  "comparability_tuples": [
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "balanced",
      "results_cut_id": "20260806_094024",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": "20260806_094024",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": "20260806_094024",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": "20260806_094024",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": "20260806_094024",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_kind": "overall"
    }
  ],
  "generated_at": "2026-08-06T09:40:24Z",
  "public_release_id": "gb2-20260806-59b3356f5989",
  "results_cut_id": "gb2-20260806-59b3356f5989",
  "rows": [
    {
      "admitted_plugins": 8,
      "attempted_matches": 914,
      "capped_draws": 1,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 1.91725,
        "mean": 1.58262125,
        "median": 1.5854,
        "min": 1.05322,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 12.660969999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 83.35739367463012,
      "contributing_entrants": null,
      "distinct_rated_opponents": 417,
      "draws": 126,
      "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": "2026-08-05T04:44:21Z",
      "losses": 143,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 68.08895739222693,
      "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": 914,
      "rating_method": "sequential_elo",
      "raw_elo": 1861.9215228524424,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 83.35739367463012,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 645
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 1086,
      "capped_draws": 2,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 3,
        "max": 2.09943,
        "mean": 1.379653125,
        "median": 1.3205149999999999,
        "min": 0.8875599999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 22.07445
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 81.79307965612657,
      "contributing_entrants": null,
      "distinct_rated_opponents": 487,
      "draws": 75,
      "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": "2026-08-05T04:52:03Z",
      "losses": 170,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 61.3843149316053,
      "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": 1086,
      "rating_method": "sequential_elo",
      "raw_elo": 1864.6719075807764,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 77.65553263999308,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 841
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 882,
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 3.2933475,
        "mean": 2.642580625,
        "median": 2.681945,
        "min": 1.562975,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.140645
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 72.12620352118518,
      "contributing_entrants": null,
      "distinct_rated_opponents": 410,
      "draws": 172,
      "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": "2026-08-05T04:44:25Z",
      "losses": 143,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 32.829666021771125,
      "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": 880,
      "rating_method": "sequential_elo",
      "raw_elo": 1811.9321887861538,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 72.12620352118518,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 565
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1646,
      "capped_draws": 24,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.551725,
        "mean": 0.44617968750000003,
        "median": 0.45788,
        "min": 0.33828,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 7.1388750000000005
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 74.34745635799887,
      "contributing_entrants": null,
      "distinct_rated_opponents": 823,
      "draws": 216,
      "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": "2026-08-05T05:35:16Z",
      "losses": 291,
      "max_score": 97.66928476084789,
      "measured_at": null,
      "min_score": 39.830660376507744,
      "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": 1646,
      "rating_method": "sequential_elo",
      "raw_elo": 1810.738566838014,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 71.90649629376915,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1139
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1742,
      "capped_draws": 132,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.5221625,
        "mean": 0.2856328125,
        "median": 0.2536225,
        "min": 0.2178175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 4.570125
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 69.78432167559475,
      "contributing_entrants": null,
      "distinct_rated_opponents": 867,
      "draws": 383,
      "entry_count": 14,
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:33:34Z",
      "losses": 289,
      "max_score": 96.50163167645941,
      "measured_at": null,
      "min_score": 46.570204853782045,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1741,
      "rating_method": "sequential_elo",
      "raw_elo": 1773.4635471348022,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 67.49317749038875,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1069
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 902,
      "capped_draws": 21,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 12.915325,
        "mean": 10.059243749999998,
        "median": 10.0094025,
        "min": 8.401555,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 80.47395
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 66.33428289138148,
      "contributing_entrants": null,
      "distinct_rated_opponents": 415,
      "draws": 101,
      "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": "2026-08-05T04:22:45Z",
      "losses": 247,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 19.935559087203618,
      "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": 902,
      "rating_method": "sequential_elo",
      "raw_elo": 1703.0249169525546,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 66.33428289138148,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 554
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 864,
      "capped_draws": 20,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 1.38945,
        "mean": 0.93123625,
        "median": 0.95991,
        "min": 0.36561,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 7.449890000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 68.15597422847155,
      "contributing_entrants": null,
      "distinct_rated_opponents": 398,
      "draws": 109,
      "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": "2026-08-05T04:43:45Z",
      "losses": 223,
      "max_score": 86.15355149666183,
      "measured_at": null,
      "min_score": 49.197008068659926,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 864,
      "rating_method": "sequential_elo",
      "raw_elo": 1724.589320143444,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 65.9182916044786,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 532
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 758,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.6981,
        "mean": 0.5046499999999999,
        "median": 0.511355,
        "min": 0.33027,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.0371999999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 67.61938022412934,
      "contributing_entrants": null,
      "distinct_rated_opponents": 377,
      "draws": 88,
      "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": "2026-08-05T04:34:24Z",
      "losses": 178,
      "max_score": 80.83296452654382,
      "measured_at": null,
      "min_score": 48.695876476828644,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 754,
      "rating_method": "sequential_elo",
      "raw_elo": 1739.5911437560183,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 65.3993149417304,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 488
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 793,
      "capped_draws": 60,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 4.4173,
        "mean": 2.7356843750000004,
        "median": 2.536595,
        "min": 2.045485,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.885475
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 66.32419996398228,
      "contributing_entrants": null,
      "distinct_rated_opponents": 377,
      "draws": 153,
      "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": "2026-08-05T04:44:25Z",
      "losses": 171,
      "max_score": 90.99516388242985,
      "measured_at": null,
      "min_score": 12.006801731616441,
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 792,
      "rating_method": "sequential_elo",
      "raw_elo": 1769.9698024775964,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 64.14665776772328,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 468
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 872,
      "capped_draws": 10,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.6689649999999999,
        "mean": 0.46799875,
        "median": 0.4352825,
        "min": 0.36661499999999997,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 4.11992
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 58.478968093175965,
      "contributing_entrants": null,
      "distinct_rated_opponents": 436,
      "draws": 190,
      "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": "2026-08-05T05:03:35Z",
      "losses": 218,
      "max_score": 85.08346922744767,
      "measured_at": null,
      "min_score": 32.39551820970374,
      "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": 872,
      "rating_method": "sequential_elo",
      "raw_elo": 1671.2669144348458,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 56.782115654344075,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 464
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": 2065,
      "capped_draws": 46,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 54
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.15843093333333336,
        "mean": 0.1253849,
        "median": 0.12730913333333332,
        "min": 0.06204813333333333,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 54
        },
        "recorded_attempt_count": 54,
        "run_count": 24,
        "total": 3.0092376000000005
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 58.330562486741115,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1026,
      "draws": 455,
      "entry_count": 21,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 18,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:56:24Z",
      "losses": 491,
      "max_score": 88.85644622319035,
      "measured_at": null,
      "min_score": 33.28968021864736,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 3,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 0.875,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2051,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.1364625728474,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 3,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 56.41546571640121,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 1105
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 906,
      "capped_draws": 57,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 12.137519999999999,
        "mean": 8.1660015625,
        "median": 8.18098,
        "min": 4.7142525,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 65.3280125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 55.34391807732854,
      "contributing_entrants": null,
      "distinct_rated_opponents": 424,
      "draws": 187,
      "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": "2026-08-05T04:35:30Z",
      "losses": 299,
      "max_score": 74.75879788264669,
      "measured_at": null,
      "min_score": 40.24489520124794,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 906,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.680291544217,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 55.34391807732854,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 420
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 878,
      "capped_draws": 81,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "max": 0.5145615,
        "mean": 0.34875300000000004,
        "median": 0.335163,
        "min": 0.254883,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 2.7900240000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.18181048687466,
      "contributing_entrants": null,
      "distinct_rated_opponents": 437,
      "draws": 277,
      "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": "2026-08-05T06:54:47Z",
      "losses": 219,
      "max_score": 88.04000833669701,
      "measured_at": null,
      "min_score": 17.608657739305404,
      "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": 874,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.0178736706696,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 52.18181048687466,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 378
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 904,
      "capped_draws": 14,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 4.987857,
        "mean": 3.1645696249999995,
        "median": 3.0710854999999997,
        "min": 1.985613,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 28.806540999999996
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 51.61421606005783,
      "contributing_entrants": null,
      "distinct_rated_opponents": 433,
      "draws": 202,
      "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": "2026-08-05T04:35:08Z",
      "losses": 292,
      "max_score": 79.30739463261588,
      "measured_at": null,
      "min_score": 22.061882688196544,
      "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": 904,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.9955654657704,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 50.11655440056413,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 410
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 906,
      "capped_draws": 97,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.15985749999999999,
        "mean": 0.09356500000000001,
        "median": 0.07461,
        "min": 0.06826499999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.74852
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.09900592574367,
      "contributing_entrants": null,
      "distinct_rated_opponents": 447,
      "draws": 341,
      "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": "2026-08-05T05:41:54Z",
      "losses": 184,
      "max_score": 97.55488190852645,
      "measured_at": null,
      "min_score": 19.60034070265804,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 900,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.0120678828102,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 50.09900592574367,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 375
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 944,
      "capped_draws": 138,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.58673,
        "mean": 0.44285687500000004,
        "median": 0.4176025,
        "min": 0.34269,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.5428550000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 48.92694853208289,
      "contributing_entrants": null,
      "distinct_rated_opponents": 472,
      "draws": 316,
      "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": "2026-08-05T05:26:46Z",
      "losses": 267,
      "max_score": 70.68089553312336,
      "measured_at": null,
      "min_score": 25.033306918921557,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 944,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.196913666888,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 48.92694853208289,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 361
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1296,
      "capped_draws": 65,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 44
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.3888165,
        "mean": 0.26060548125,
        "median": 0.24728879999999998,
        "min": 0.17802225,
        "recorded_attempt_count": 44,
        "run_count": 16,
        "total": 4.169687700000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 50.410518444816546,
      "contributing_entrants": null,
      "distinct_rated_opponents": 649,
      "draws": 375,
      "entry_count": 14,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-08"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:55:12Z",
      "losses": 303,
      "max_score": 83.67694797963125,
      "measured_at": null,
      "min_score": 17.78870942250549,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1296,
      "rating_method": "sequential_elo",
      "raw_elo": 1626.347488636587,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 48.75545089619188,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 618
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": 1194,
      "capped_draws": 26,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 50
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.19006573333333335,
        "mean": 0.11809463333333332,
        "median": 0.09664113333333335,
        "min": 0.06671613333333333,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 50
        },
        "recorded_attempt_count": 50,
        "run_count": 24,
        "total": 2.8342712000000003
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 48.905709680771956,
      "contributing_entrants": null,
      "distinct_rated_opponents": 597,
      "draws": 325,
      "entry_count": 37,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:57:05Z",
      "losses": 579,
      "max_score": 68.96755045489611,
      "measured_at": null,
      "min_score": 18.785677670777737,
      "model_code_failure_rate": 0.08333333333333333,
      "model_code_failures": 2,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 0.9166666666666666,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1194,
      "rating_method": "sequential_elo",
      "raw_elo": 1610.1661170861369,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.08333333333333333,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 47.853358704885466,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1022
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 908,
      "capped_draws": 74,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.712055,
        "mean": 0.49864374999999994,
        "median": 0.5065824999999999,
        "min": 0.29423750000000004,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.9891499999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.897011088603556,
      "contributing_entrants": null,
      "distinct_rated_opponents": 452,
      "draws": 291,
      "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": "2026-08-05T06:55:12Z",
      "losses": 240,
      "max_score": 94.87005862041984,
      "measured_at": null,
      "min_score": 17.553436099642553,
      "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": 906,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.118740708225,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 46.897011088603556,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 375
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1450,
      "capped_draws": 94,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 2,
          "local_standard_estimate": 18
        },
        "evidence_basis": "Mixed: Recorded attempt + Standard list-price estimate",
        "max": 1.5164726249999998,
        "mean": 1.0788743062500001,
        "median": 0.9700117500000001,
        "min": 0.8356068750000001,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-07-30": 18
        },
        "recorded_attempt_count": 2,
        "run_count": 14,
        "token_priced_attempt_count": 18,
        "total": 15.220633649999998
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 46.73048991131135,
      "contributing_entrants": null,
      "distinct_rated_opponents": 695,
      "draws": 362,
      "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": "2026-08-05T04:52:03Z",
      "losses": 511,
      "max_score": 72.91920929796846,
      "measured_at": null,
      "min_score": 18.231928182356505,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1450,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.5490296647502,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 2,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 46.73048991131135,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 577
    },
    {
      "admitted_plugins": 20,
      "attempted_matches": 810,
      "capped_draws": 29,
      "codegen_cost_usd": {
        "admitted_cell_count": 20,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 65
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 1.1177706,
        "mean": 0.8961934,
        "median": 0.9197228499999999,
        "min": 0.6673354000000001,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 65
        },
        "recorded_attempt_count": 65,
        "run_count": 26,
        "total": 23.267240399999995
      },
      "codegen_evaluated_cells": 25,
      "conditional_success_score": 48.43186177867785,
      "contributing_entrants": null,
      "distinct_rated_opponents": 405,
      "draws": 264,
      "entry_count": 25,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 16,
      "first_pass_rate": 0.64,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_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": "2026-08-05T06:57:15Z",
      "losses": 249,
      "max_score": 76.9153537911332,
      "measured_at": null,
      "min_score": 20.09827284833638,
      "model_code_failure_rate": 0.2,
      "model_code_failures": 5,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 0.8,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 810,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.0233363316154,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 4,
      "repaired_rate": 0.16,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 45.804026885586204,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 491
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 948,
      "capped_draws": 109,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.144235,
        "mean": 0.12174125,
        "median": 0.121475,
        "min": 0.09594,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.9739299999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 45.30926050948271,
      "contributing_entrants": null,
      "distinct_rated_opponents": 473,
      "draws": 329,
      "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": "2026-08-05T05:02:30Z",
      "losses": 263,
      "max_score": 64.91944958274557,
      "measured_at": null,
      "min_score": 25.69560465698689,
      "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": 948,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.244847449798,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 45.30926050948271,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 356
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 641,
      "capped_draws": 69,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.531673125,
        "mean": 0.47737264687500003,
        "median": 0.48302475,
        "min": 0.3855675,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 7.6379623500000005
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 48.607615644623934,
      "contributing_entrants": null,
      "distinct_rated_opponents": 321,
      "draws": 182,
      "entry_count": 24,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-07"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:56:18Z",
      "losses": 321,
      "max_score": 72.5401989690437,
      "measured_at": null,
      "min_score": 35.01219161214689,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 641,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.3973922391638,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 45.23448330825427,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 532
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 1120,
      "capped_draws": 107,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.4567,
        "mean": 0.3802064166666667,
        "median": 0.3908776666666667,
        "min": 0.234622,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 10,
        "token_priced_attempt_count": 11,
        "total": 3.8844619999999996
      },
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 44.378482409071644,
      "contributing_entrants": null,
      "distinct_rated_opponents": 530,
      "draws": 350,
      "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": "2026-08-05T04:45:00Z",
      "losses": 411,
      "max_score": 62.31323923781224,
      "measured_at": null,
      "min_score": 29.014574794367363,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1120,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.644384166015,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 44.378482409071644,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 359
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 1032,
      "capped_draws": 103,
      "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,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 17
        },
        "recorded_attempt_count": 17,
        "run_count": 16,
        "total": 1.1192034
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 43.84198067135024,
      "contributing_entrants": null,
      "distinct_rated_opponents": 516,
      "draws": 477,
      "entry_count": 32,
      "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": "2026-08-05T06:56:40Z",
      "losses": 441,
      "max_score": 62.82646209967631,
      "measured_at": null,
      "min_score": 17.703162245681458,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1032,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.8327117008246,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 43.84198067135024,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 710
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 858,
      "capped_draws": 42,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.244315,
        "mean": 0.178065,
        "median": 0.19681749999999998,
        "min": 0.10277,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.4245200000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.52801384089684,
      "contributing_entrants": null,
      "distinct_rated_opponents": 428,
      "draws": 523,
      "entry_count": 16,
      "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": "2026-08-05T06:57:11Z",
      "losses": 502,
      "max_score": 59.511553845816714,
      "measured_at": null,
      "min_score": 25.99852516396363,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 857,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.7350238553536,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 43.52801384089684,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 566
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 786,
      "capped_draws": 28,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.190125,
        "mean": 0.15785312499999998,
        "median": 0.15388000000000002,
        "min": 0.131495,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.2628249999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.39353927490981,
      "contributing_entrants": null,
      "distinct_rated_opponents": 391,
      "draws": 198,
      "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": "2026-08-05T03:47:33Z",
      "losses": 246,
      "max_score": 68.98590691472927,
      "measured_at": null,
      "min_score": 17.488893388132354,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 786,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.0231928444312,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 42.93601992202062,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 342
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 930,
      "capped_draws": 131,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.046574000000000004,
        "mean": 0.036155625000000004,
        "median": 0.035338,
        "min": 0.025803,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 0.315048
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 43.72233320991606,
      "contributing_entrants": null,
      "distinct_rated_opponents": 464,
      "draws": 363,
      "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": "2026-08-05T05:17:39Z",
      "losses": 268,
      "max_score": 65.53875120306154,
      "measured_at": null,
      "min_score": 20.419129829006703,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 928,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.3394240446828,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 42.45366602652019,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 297
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 918,
      "capped_draws": 131,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.34174499999999997,
        "mean": 0.217940625,
        "median": 0.19638,
        "min": 0.14813,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.743525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.28532376648441,
      "contributing_entrants": null,
      "distinct_rated_opponents": 459,
      "draws": 357,
      "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": "2026-08-05T03:49:27Z",
      "losses": 247,
      "max_score": 81.9183167340137,
      "measured_at": null,
      "min_score": 16.591663020618228,
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 918,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.8427047975565,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 42.28532376648441,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 314
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 888,
      "capped_draws": 50,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.147405,
        "mean": 0.12146437500000001,
        "median": 0.124865,
        "min": 0.09045,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 1.069485
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 43.37417866830484,
      "contributing_entrants": null,
      "distinct_rated_opponents": 440,
      "draws": 237,
      "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": "2026-08-05T05:17:02Z",
      "losses": 293,
      "max_score": 59.006818274433016,
      "measured_at": null,
      "min_score": 29.15647522370581,
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 882,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.2154838477545,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 42.11561369605062,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 352
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 868,
      "capped_draws": 80,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.11634299999999999,
        "mean": 0.07787519999999999,
        "median": 0.0843883,
        "min": 0.041110400000000005,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 28
        },
        "recorded_attempt_count": 28,
        "run_count": 16,
        "total": 1.2460031999999999
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 42.02398603997369,
      "contributing_entrants": null,
      "distinct_rated_opponents": 434,
      "draws": 391,
      "entry_count": 30,
      "failed_game_aliases": [
        "GB2-04"
      ],
      "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": "2026-08-05T06:56:18Z",
      "losses": 372,
      "max_score": 61.644694598987854,
      "measured_at": null,
      "min_score": 16.238936021776848,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 0.9375,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 868,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.9368813771428,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 41.35138523603543,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 583
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 1728,
      "capped_draws": 252,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 2,
          "local_standard_estimate": 29
        },
        "evidence_basis": "Mixed: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.38568888333333334,
        "mean": 0.288318396875,
        "median": 0.28604548333333335,
        "min": 0.22385259999999998,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-07-30": 29
        },
        "recorded_attempt_count": 2,
        "run_count": 20,
        "token_priced_attempt_count": 29,
        "total": 5.92105485
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": 42.5715192844583,
      "contributing_entrants": null,
      "distinct_rated_opponents": 830,
      "draws": 510,
      "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": "2026-08-05T04:43:45Z",
      "losses": 649,
      "max_score": 88.3001049099167,
      "measured_at": null,
      "min_score": 18.002828160874977,
      "model_code_failure_rate": 0.11764705882352941,
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1727,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.9596145279502,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 5,
      "repaired_rate": 0.29411764705882354,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 41.26004847678181,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 568
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 748,
      "capped_draws": 113,
      "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": 43.9705511062461,
      "contributing_entrants": null,
      "distinct_rated_opponents": 361,
      "draws": 177,
      "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": "2026-08-05T05:11:41Z",
      "losses": 304,
      "max_score": 76.14344213568862,
      "measured_at": null,
      "min_score": 25.042469828678968,
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 748,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.6070630471286,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 40.919208516869816,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 267
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 1042,
      "capped_draws": 248,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 1,
          "local_list_price_estimate": 8,
          "provider_dashboard_reconciled": 1
        },
        "evidence_basis": "Mixed: Provider-reported + Recorded attempt + Standard list-price estimate",
        "max": 0.07806,
        "mean": 0.062955625,
        "median": 0.061544,
        "min": 0.049788,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "recorded_attempt_count": 2,
        "run_count": 9,
        "token_priced_attempt_count": 8,
        "total": 0.57987
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 40.65157086620186,
      "contributing_entrants": null,
      "distinct_rated_opponents": 518,
      "draws": 468,
      "entry_count": 9,
      "failed_game_aliases": [],
      "first_pass_admitted": 9,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:08Z",
      "losses": 275,
      "max_score": 57.99889288812461,
      "measured_at": null,
      "min_score": 24.09530085961754,
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1042,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.647139762114,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 40.65157086620186,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 299
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 944,
      "capped_draws": 102,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.24673750000000003,
        "mean": 0.16744,
        "median": 0.15809499999999999,
        "min": 0.108735,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 1.3395199999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.424571316358005,
      "contributing_entrants": null,
      "distinct_rated_opponents": 472,
      "draws": 348,
      "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": "2026-08-05T06:54:57Z",
      "losses": 289,
      "max_score": 52.65682323634443,
      "measured_at": null,
      "min_score": 25.620832892368888,
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 944,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.7548256127336,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 40.424571316358005,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 307
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 776,
      "capped_draws": 95,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.072978,
        "mean": 0.048872,
        "median": 0.046325000000000005,
        "min": 0.037309999999999996,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.390976
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.180486700957516,
      "contributing_entrants": null,
      "distinct_rated_opponents": 388,
      "draws": 194,
      "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": "2026-08-05T05:17:46Z",
      "losses": 281,
      "max_score": 57.446840898177854,
      "measured_at": null,
      "min_score": 24.604745440205885,
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 776,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.6004371597362,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 40.18397074230465,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 6,
      "attempted_matches": 382,
      "capped_draws": 41,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.2996388,
        "mean": 0.13471628689999998,
        "median": 0.1144847257,
        "min": 0.027613287599999998,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 1.0777302952
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.065196543476866,
      "contributing_entrants": null,
      "distinct_rated_opponents": 191,
      "draws": 175,
      "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": "2026-08-05T05:28:30Z",
      "losses": 308,
      "max_score": 66.15885507474644,
      "measured_at": null,
      "min_score": 19.35129652009281,
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 382,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.1960904346722,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 40.07668116154651,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 289
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 466,
      "capped_draws": 76,
      "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": 0.43500896000000006
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.51498698617433,
      "contributing_entrants": null,
      "distinct_rated_opponents": 233,
      "draws": 253,
      "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": "2026-08-05T03:48:47Z",
      "losses": 259,
      "max_score": 69.54336053342072,
      "measured_at": null,
      "min_score": 19.793619316293615,
      "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": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 466,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.1709934250127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 39.56465347399636,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 268
    },
    {
      "admitted_plugins": 20,
      "attempted_matches": 2195,
      "capped_draws": 277,
      "codegen_cost_usd": {
        "admitted_cell_count": 20,
        "cell_count": 8,
        "cost_basis_counts": {
          "exact_cumulative_delta": 1,
          "provider_reported": 64
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.25823185295,
        "mean": 0.20846239076375003,
        "median": 0.20662718916666667,
        "min": 0.13654539825,
        "recorded_attempt_count": 65,
        "run_count": 29,
        "total": 5.97530434986
      },
      "codegen_evaluated_cells": 27,
      "conditional_success_score": 42.31385173430746,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1053,
      "draws": 713,
      "entry_count": 20,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.1111111111111111,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_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": "2026-08-05T05:05:01Z",
      "losses": 790,
      "max_score": 76.82222311841032,
      "measured_at": null,
      "min_score": 20.17228110668475,
      "model_code_failure_rate": 0.25925925925925924,
      "model_code_failures": 7,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 0.7407407407407407,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2187,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.2952285458111,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 17,
      "repaired_rate": 0.6296296296296297,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 39.2553738606206,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 8,
      "wins": 684
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": 2758,
      "capped_draws": 325,
      "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": 0.29749325000000004,
        "mean": 0.24155631250000004,
        "median": 0.24021375,
        "min": 0.17873725,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 26
        },
        "run_count": 24,
        "token_priced_attempt_count": 26,
        "total": 5.7973514999999995
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 39.16874370300505,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1377,
      "draws": 947,
      "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": "2026-08-05T06:55:18Z",
      "losses": 963,
      "max_score": 60.20667295526242,
      "measured_at": null,
      "min_score": 22.192579972734823,
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2754,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.498604622192,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.754201302051065,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 844
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 489,
      "capped_draws": 45,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.45464499999999997,
        "mean": 0.28201406249999994,
        "median": 0.2695775,
        "min": 0.17401125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 2.2561125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.58016390752029,
      "contributing_entrants": null,
      "distinct_rated_opponents": 244,
      "draws": 303,
      "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": "2026-08-05T05:05:23Z",
      "losses": 324,
      "max_score": 66.50580979104048,
      "measured_at": null,
      "min_score": 16.793318043756123,
      "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": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 488,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.6253461342465,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.58016390752029,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 309
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 932,
      "capped_draws": 138,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.1192425,
        "mean": 0.0683559375,
        "median": 0.06152125,
        "min": 0.0542775,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 0.6063374999999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 39.69550753752692,
      "contributing_entrants": null,
      "distinct_rated_opponents": 462,
      "draws": 363,
      "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": "2026-08-05T03:05:30Z",
      "losses": 296,
      "max_score": 52.63127668910358,
      "measured_at": null,
      "min_score": 28.273880023544745,
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 930,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.8160766249243,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.54368456643071,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 271
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 370,
      "capped_draws": 36,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.6921525,
        "mean": 0.48907706250000005,
        "median": 0.483741,
        "min": 0.401826,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 3.9126164999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.41206956369944,
      "contributing_entrants": null,
      "distinct_rated_opponents": 185,
      "draws": 182,
      "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": "2026-08-05T05:04:52Z",
      "losses": 250,
      "max_score": 77.86243893295662,
      "measured_at": null,
      "min_score": 12.88406623711618,
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 370,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.7605198475023,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.538273161452864,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 234
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 794,
      "capped_draws": 93,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.21477374999999999,
        "mean": 0.17756265624999998,
        "median": 0.17285124999999998,
        "min": 0.1418975,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 1.42050125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.611716088428516,
      "contributing_entrants": null,
      "distinct_rated_opponents": 397,
      "draws": 220,
      "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": "2026-08-05T05:19:06Z",
      "losses": 303,
      "max_score": 57.96187879269228,
      "measured_at": null,
      "min_score": 20.440337873964644,
      "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": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 794,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.5045582427992,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.31119254957503,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 271
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 818,
      "capped_draws": 138,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.03912625,
        "mean": 0.022799843750000003,
        "median": 0.021642500000000002,
        "min": 0.015285,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.18239874999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.493085531119945,
      "contributing_entrants": null,
      "distinct_rated_opponents": 401,
      "draws": 281,
      "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": "2026-08-05T05:33:39Z",
      "losses": 272,
      "max_score": 68.55479086064098,
      "measured_at": null,
      "min_score": 22.482461561801962,
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 812,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.9753327208534,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.19645684579572,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 259
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 884,
      "capped_draws": 117,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.132112,
        "mean": 0.0780535,
        "median": 0.06797,
        "min": 0.05673,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.6244280000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.446348181834175,
      "contributing_entrants": null,
      "distinct_rated_opponents": 442,
      "draws": 293,
      "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": "2026-08-05T04:04:02Z",
      "losses": 264,
      "max_score": 52.20111840015675,
      "measured_at": null,
      "min_score": 22.62500365197257,
      "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": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 884,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.0178904372638,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.1512539673406,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 327
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 830,
      "capped_draws": 161,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.029078938,
        "mean": 0.015562441375000001,
        "median": 0.013116718500000001,
        "min": 0.005612805,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.12449953100000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.82358458571298,
      "contributing_entrants": null,
      "distinct_rated_opponents": 408,
      "draws": 289,
      "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": "2026-08-05T04:27:08Z",
      "losses": 266,
      "max_score": 67.31147896345796,
      "measured_at": null,
      "min_score": 17.2055412078098,
      "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": 830,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.7125262755892,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 37.548936814743556,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 275
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 686,
      "capped_draws": 50,
      "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": 38.62762612577164,
      "contributing_entrants": null,
      "distinct_rated_opponents": 340,
      "draws": 175,
      "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": "2026-08-05T05:17:07Z",
      "losses": 254,
      "max_score": 52.11814186315531,
      "measured_at": null,
      "min_score": 25.43537970074668,
      "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": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 686,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.4598024034094,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.2857142857142857,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 37.167326419101414,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 257
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 808,
      "capped_draws": 103,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 32
        },
        "evidence_basis": "Provider-reported",
        "max": 0.3926418,
        "mean": 0.31750829999999997,
        "median": 0.32150055,
        "min": 0.2298153,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 32
        },
        "recorded_attempt_count": 32,
        "run_count": 16,
        "total": 5.0801327999999994
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 37.13772805268788,
      "contributing_entrants": null,
      "distinct_rated_opponents": 397,
      "draws": 436,
      "entry_count": 32,
      "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": "2026-08-05T06:56:50Z",
      "losses": 438,
      "max_score": 56.503902002777224,
      "measured_at": null,
      "min_score": 19.738580505271273,
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 794,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.73885911828,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 37.13772805268788,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 6,
      "attempted_matches": 452,
      "capped_draws": 6,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.226689264,
        "mean": 0.16037539425,
        "median": 0.140728509,
        "min": 0.10689655,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 1.283003154
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.809027678930654,
      "contributing_entrants": null,
      "distinct_rated_opponents": 226,
      "draws": 213,
      "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": "2026-08-05T05:26:41Z",
      "losses": 262,
      "max_score": 54.35480356946494,
      "measured_at": null,
      "min_score": 20.78553102586511,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": 0.75,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 452,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.5960235384453,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 37.04647459414284,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 291
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 528,
      "capped_draws": 68,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.12185499999999999,
        "mean": 0.09110296875000001,
        "median": 0.09280125,
        "min": 0.0343775,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.7288237500000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.11427405995131,
      "contributing_entrants": null,
      "distinct_rated_opponents": 264,
      "draws": 324,
      "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": "2026-08-05T05:35:11Z",
      "losses": 291,
      "max_score": 63.864244753090226,
      "measured_at": null,
      "min_score": 20.42853187574935,
      "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": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 528,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.2572018908854,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 36.862914223113556,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 271
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 934,
      "capped_draws": 107,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.09459400000000001,
        "mean": 0.0571955,
        "median": 0.043012,
        "min": 0.032534,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 0.457564
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.39316993293499,
      "contributing_entrants": null,
      "distinct_rated_opponents": 463,
      "draws": 324,
      "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": "2026-08-05T05:41:31Z",
      "losses": 336,
      "max_score": 56.63398289929676,
      "measured_at": null,
      "min_score": 14.75877111394388,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 933,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.6731004328792,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 36.39316993293499,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 273
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1476,
      "capped_draws": 310,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.00407402,
        "mean": 0.0029986699999999997,
        "median": 0.00314426,
        "min": 0.0012446800000000002,
        "recorded_attempt_count": 33,
        "run_count": 14,
        "total": 0.04176386
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 37.41625726018497,
      "contributing_entrants": null,
      "distinct_rated_opponents": 719,
      "draws": 510,
      "entry_count": 12,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:40:59Z",
      "losses": 500,
      "max_score": 52.809153048377176,
      "measured_at": null,
      "min_score": 21.571994896490278,
      "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": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1465,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.326306325724,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 5,
      "repaired_rate": 0.35714285714285715,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 36.00175279843416,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 455
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 544,
      "capped_draws": 120,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.0222516,
        "mean": 0.01697319375,
        "median": 0.015739925000000002,
        "min": 0.012759,
        "recorded_attempt_count": 34,
        "run_count": 16,
        "total": 0.27157109999999995
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.569696137032814,
      "contributing_entrants": null,
      "distinct_rated_opponents": 271,
      "draws": 476,
      "entry_count": 30,
      "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": "2026-08-05T05:41:49Z",
      "losses": 403,
      "max_score": 58.42525560215735,
      "measured_at": null,
      "min_score": 16.907630545609305,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.9375,
      "provider": "Google",
      "provider_key": "google",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 542,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.4671465202425,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 35.98439213949794,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 346
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 844,
      "capped_draws": 218,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.156555,
        "mean": 0.1422525,
        "median": 0.14850249999999998,
        "min": 0.12078,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.13802
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.189039884034734,
      "contributing_entrants": null,
      "distinct_rated_opponents": 417,
      "draws": 432,
      "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": "2026-08-05T05:23:57Z",
      "losses": 213,
      "max_score": 51.11478815980904,
      "measured_at": null,
      "min_score": 23.30438447793437,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 844,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.0171483481488,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 35.968057141237665,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 1072,
      "capped_draws": 84,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 32,
          "local_standard_estimate": 8
        },
        "evidence_basis": "Mixed: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 13,
        "max": 0.1097735,
        "mean": 0.091486,
        "median": 0.08840574999999999,
        "min": 0.07737849999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 40
        },
        "recorded_attempt_count": 32,
        "run_count": 32,
        "token_priced_attempt_count": 8,
        "total": 2.9275519999999995
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 40.42513666720264,
      "contributing_entrants": null,
      "distinct_rated_opponents": 534,
      "draws": 156,
      "entry_count": 38,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 19,
      "first_pass_rate": 0.59375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:56:55Z",
      "losses": 751,
      "max_score": 47.24502914491117,
      "measured_at": null,
      "min_score": 32.4038428924734,
      "model_code_failure_rate": 0.40625,
      "model_code_failures": 13,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.59375,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1068,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.9077340839624,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 35.48562040144815,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 714
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 633,
      "capped_draws": 133,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "evidence_basis": "Provider-reported",
        "max": 0.07826175,
        "mean": 0.05584070625,
        "median": 0.0541695,
        "min": 0.0411735,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 0.8934513000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 35.192117790614326,
      "contributing_entrants": null,
      "distinct_rated_opponents": 313,
      "draws": 568,
      "entry_count": 32,
      "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": "2026-08-05T06:56:02Z",
      "losses": 413,
      "max_score": 51.56860730824784,
      "measured_at": null,
      "min_score": 15.356957668247802,
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 626,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.3736824777882,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 35.192117790614326,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 6,
      "attempted_matches": 720,
      "capped_draws": 42,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.09803328,
        "mean": 0.0253809975,
        "median": 0.00943521,
        "min": 0.00639384,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.20304798000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.27597496645672,
      "contributing_entrants": null,
      "distinct_rated_opponents": 358,
      "draws": 170,
      "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": "2026-08-05T04:33:21Z",
      "losses": 266,
      "max_score": 49.2908922032663,
      "measured_at": null,
      "min_score": 17.49414607975783,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": 0.75,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 720,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.8610454137633,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 34.68920343155285,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 284
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 474,
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.73533,
        "mean": 0.5886581249999999,
        "median": 0.58241,
        "min": 0.410635,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.709265
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.556285952613884,
      "contributing_entrants": null,
      "distinct_rated_opponents": 237,
      "draws": 204,
      "entry_count": 16,
      "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": "2026-08-05T05:28:52Z",
      "losses": 329,
      "max_score": 51.73002467422387,
      "measured_at": null,
      "min_score": 11.592420116905998,
      "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": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 474,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.6964641199188,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 33.556285952613884,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 259
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 684,
      "capped_draws": 131,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.001632522,
        "mean": 0.00126739675,
        "median": 0.001232095,
        "min": 0.00090937,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.010139173999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.3872173535151,
      "contributing_entrants": null,
      "distinct_rated_opponents": 336,
      "draws": 307,
      "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": "2026-08-05T05:08:37Z",
      "losses": 178,
      "max_score": 72.251918530255,
      "measured_at": null,
      "min_score": 13.313054666786927,
      "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": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 678,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.5629379610066,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 32.93151641928329,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 193
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 578,
      "capped_draws": 70,
      "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": 32.35197445455003,
      "contributing_entrants": null,
      "distinct_rated_opponents": 289,
      "draws": 369,
      "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": "2026-08-05T05:34:43Z",
      "losses": 345,
      "max_score": 53.061970706152835,
      "measured_at": null,
      "min_score": 19.32369832555091,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 578,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.0169648040564,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 32.35197445455003,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 266
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 1294,
      "capped_draws": 146,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.017371818,
        "mean": 0.00989701923,
        "median": 0.010218342,
        "min": 0.003562685,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 0.15835230767999997
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": 34.783090077371796,
      "contributing_entrants": null,
      "distinct_rated_opponents": 628,
      "draws": 314,
      "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": "2026-08-05T04:43:54Z",
      "losses": 598,
      "max_score": 54.873388733034076,
      "measured_at": null,
      "min_score": 21.713702201359574,
      "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": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1294,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.5820692435125,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 6,
      "repaired_rate": 0.4,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 32.18796481877993,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 382
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1462,
      "capped_draws": 132,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0721503,
        "mean": 0.03677837187500001,
        "median": 0.0324098875,
        "min": 0.01945095,
        "recorded_attempt_count": 39,
        "run_count": 16,
        "total": 0.5884539500000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 34.48501987666433,
      "contributing_entrants": null,
      "distinct_rated_opponents": 715,
      "draws": 468,
      "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": "2026-08-05T05:41:54Z",
      "losses": 569,
      "max_score": 62.96894118841835,
      "measured_at": null,
      "min_score": 17.986293369286603,
      "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": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1461,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.989123005506,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 32.09192706345631,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 424
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1884,
      "capped_draws": 258,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0097359,
        "mean": 0.0038356840999999994,
        "median": 0.0020557588,
        "min": 0.0014804776,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.030685472800000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.33105017629488,
      "contributing_entrants": null,
      "distinct_rated_opponents": 937,
      "draws": 555,
      "entry_count": 17,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:45Z",
      "losses": 738,
      "max_score": 48.233162638067576,
      "measured_at": null,
      "min_score": 20.22265746079894,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.75,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1882,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.4549430232298,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 31.948642112138007,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 589
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 306,
      "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": 36.64777963132047,
      "contributing_entrants": null,
      "distinct_rated_opponents": 152,
      "draws": 95,
      "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": "2026-08-05T03:57:18Z",
      "losses": 224,
      "max_score": 49.01545827784715,
      "measured_at": null,
      "min_score": 24.21197020273949,
      "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": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 304,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.9344834422477,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 4,
      "repaired_rate": 0.5714285714285714,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 31.863109432351056,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 205
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1728,
      "capped_draws": 352,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 38
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.021206376000000002,
        "mean": 0.01337795025,
        "median": 0.01381146,
        "min": 0.006392298,
        "recorded_attempt_count": 38,
        "run_count": 16,
        "total": 0.21404720400000002
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 32.92807444254993,
      "contributing_entrants": null,
      "distinct_rated_opponents": 842,
      "draws": 622,
      "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": "2026-08-05T05:41:26Z",
      "losses": 645,
      "max_score": 48.45429450824968,
      "measured_at": null,
      "min_score": 13.789037064172394,
      "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": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1724,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.3765675707743,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 31.84698682175468,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 457
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 831,
      "capped_draws": 139,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00444719,
        "mean": 0.0024656575,
        "median": 0.002155255,
        "min": 0.0011302579999999999,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.019725259999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.58613741833025,
      "contributing_entrants": null,
      "distinct_rated_opponents": 416,
      "draws": 377,
      "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": "2026-08-05T04:12:06Z",
      "losses": 280,
      "max_score": 43.16059564656367,
      "measured_at": null,
      "min_score": 21.765095786368434,
      "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": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 831,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.9706567381093,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 30.54910799192781,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 174
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 592,
      "capped_draws": 48,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 50
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0719635,
        "mean": 0.060768406250000004,
        "median": 0.0604727,
        "min": 0.05086675,
        "recorded_attempt_count": 50,
        "run_count": 16,
        "total": 0.9722945000000002
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 30.677141499448677,
      "contributing_entrants": null,
      "distinct_rated_opponents": 294,
      "draws": 250,
      "entry_count": 26,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.8125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:56:50Z",
      "losses": 433,
      "max_score": 44.976480556909316,
      "measured_at": null,
      "min_score": 18.1638721019117,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 588,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.6502948560828,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 29.66995603604416,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 283
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 2895,
      "capped_draws": 476,
      "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-2026-07-30": 56
        },
        "run_count": 32,
        "token_priced_attempt_count": 56,
        "total": 0.28794675000000003
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 31.371594744143064,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1426,
      "draws": 1130,
      "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": "2026-08-05T05:41:31Z",
      "losses": 1053,
      "max_score": 56.65051046409322,
      "measured_at": null,
      "min_score": 19.59118479048314,
      "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": 2888,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.9585326737122,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 15,
      "repaired_rate": 0.46875,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 29.494029057469312,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 705
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 2864,
      "capped_draws": 257,
      "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": 0.02520601875,
        "min": 0.0165820625,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 49
        },
        "run_count": 32,
        "token_priced_attempt_count": 49,
        "total": 0.7792869
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 31.30438245280745,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1430,
      "draws": 728,
      "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": "2026-08-05T06:55:07Z",
      "losses": 1330,
      "max_score": 56.30542073431529,
      "measured_at": null,
      "min_score": 15.510539068363032,
      "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": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2860,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.4044341064155,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 12,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 29.43083936979678,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 802
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 578,
      "capped_draws": 116,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 21
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.065385,
        "mean": 0.03551179375,
        "median": 0.032728425,
        "min": 0.0200767,
        "recorded_attempt_count": 21,
        "run_count": 9,
        "total": 0.3177278
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 34.035872155662275,
      "contributing_entrants": null,
      "distinct_rated_opponents": 289,
      "draws": 222,
      "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": "2026-08-05T03:41:43Z",
      "losses": 207,
      "max_score": 61.2479202482627,
      "measured_at": null,
      "min_score": 14.05665305055863,
      "model_code_failure_rate": 0.4444444444444444,
      "model_code_failures": 4,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": 0.5555555555555556,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 578,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.1265922885773,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 5,
      "repaired_rate": 0.5555555555555556,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 29.38453059423139,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 518,
      "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": 2,
        "max": 0.038769960000000006,
        "mean": 0.023744302225,
        "median": 0.0230069837,
        "min": 0.0074361952000000005,
        "recorded_attempt_count": 20,
        "run_count": 9,
        "total": 0.21411433159999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 31.163958349814212,
      "contributing_entrants": null,
      "distinct_rated_opponents": 259,
      "draws": 274,
      "entry_count": 14,
      "failed_game_aliases": [
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:57:10Z",
      "losses": 356,
      "max_score": 36.61730356084032,
      "measured_at": null,
      "min_score": 20.671691142857387,
      "model_code_failure_rate": 0.2222222222222222,
      "model_code_failures": 2,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.7777777777777778,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 518,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.1836553756668,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 7,
      "repaired_rate": 0.7777777777777778,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 29.26621089867655,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 280
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 2773,
      "capped_draws": 401,
      "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-2026-07-30": 29
        },
        "run_count": 24,
        "token_priced_attempt_count": 29,
        "total": 0.4149345
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 28.626949132145135,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1367,
      "draws": 1133,
      "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": "2026-08-05T05:33:34Z",
      "losses": 1021,
      "max_score": 39.007466418277744,
      "measured_at": null,
      "min_score": 16.762689788970278,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2766,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.2054971572938,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333334,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 28.626949132145135,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 7,
      "wins": 612
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 2170,
      "capped_draws": 348,
      "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": 0.0018257240000000001,
        "recorded_attempt_count": 34,
        "run_count": 24,
        "total": 0.053353921299999996
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 30.337491687517996,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1073,
      "draws": 868,
      "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": "2026-08-05T05:41:49Z",
      "losses": 797,
      "max_score": 40.791267003138834,
      "measured_at": null,
      "min_score": 21.33030113424673,
      "model_code_failure_rate": 0.20833333333333334,
      "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": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2170,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.1868857638447,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333334,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 28.616417290149574,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 505
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 746,
      "capped_draws": 146,
      "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": 29.708758518921826,
      "contributing_entrants": null,
      "distinct_rated_opponents": 365,
      "draws": 240,
      "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": "2026-08-05T03:48:11Z",
      "losses": 302,
      "max_score": 41.22577138332814,
      "measured_at": null,
      "min_score": 19.625108861534393,
      "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": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 744,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.5128996597357,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.14285714285714285,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 28.585632515541217,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 202
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 442,
      "capped_draws": 20,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.007539277999999999,
        "mean": 0.0032457859375,
        "median": 0.0019568429999999998,
        "min": 0.001266762,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 0.031586439
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 30.2637506304396,
      "contributing_entrants": null,
      "distinct_rated_opponents": 220,
      "draws": 207,
      "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": "2026-08-05T05:11:51Z",
      "losses": 373,
      "max_score": 53.57176981147765,
      "measured_at": null,
      "min_score": 6.649465460691646,
      "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": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 440,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.2072714576009,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 28.420821854316237,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 246
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 320,
      "capped_draws": 38,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.01660212,
        "mean": 0.008820586750000001,
        "median": 0.007023681,
        "min": 0.00271606,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.07056469400000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.34390555147243,
      "contributing_entrants": null,
      "distinct_rated_opponents": 160,
      "draws": 218,
      "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": "2026-08-05T05:11:31Z",
      "losses": 194,
      "max_score": 64.6891432709365,
      "measured_at": null,
      "min_score": 10.34354662706081,
      "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": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.926620752997,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 27.869110936194055,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 14,
      "attempted_matches": 1163,
      "capped_draws": 194,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 48
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0481474,
        "mean": 0.03800683125,
        "median": 0.037386975,
        "min": 0.02957195,
        "recorded_attempt_count": 48,
        "run_count": 16,
        "total": 0.6081093000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.357331660578332,
      "contributing_entrants": null,
      "distinct_rated_opponents": 581,
      "draws": 452,
      "entry_count": 14,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:55:18Z",
      "losses": 478,
      "max_score": 42.286286758943646,
      "measured_at": null,
      "min_score": 19.020552189812655,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1159,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.084433447604,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 26.459141496199234,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 229
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 586,
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 70
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.103943664,
        "mean": 0.0866474535,
        "median": 0.088847748,
        "min": 0.062759676,
        "recorded_attempt_count": 70,
        "run_count": 16,
        "total": 1.386359256
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.9422064022846,
      "contributing_entrants": null,
      "distinct_rated_opponents": 290,
      "draws": 212,
      "entry_count": 24,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:54:28Z",
      "losses": 449,
      "max_score": 37.8518501101937,
      "measured_at": null,
      "min_score": 11.347553349665287,
      "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": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 578,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.8160500613042,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 26.003153051999846,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 8,
      "wins": 271
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 764,
      "capped_draws": 110,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0149315,
        "mean": 0.0101355,
        "median": 0.010566625,
        "min": 0.00402875,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 0.08108399999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 27.748939787173324,
      "contributing_entrants": null,
      "distinct_rated_opponents": 381,
      "draws": 203,
      "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": "2026-08-05T05:18:42Z",
      "losses": 377,
      "max_score": 41.949273557550775,
      "measured_at": null,
      "min_score": 4.666816393696632,
      "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": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 762,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.2852200609302,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 25.823298200875076,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 182
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 464,
      "capped_draws": 86,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0068074,
        "mean": 0.0034371900000000006,
        "median": 0.00326368,
        "min": 0.00211404,
        "recorded_attempt_count": 35,
        "run_count": 14,
        "total": 0.04917795999999999
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 27.22318762550223,
      "contributing_entrants": null,
      "distinct_rated_opponents": 231,
      "draws": 407,
      "entry_count": 22,
      "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": "2026-08-05T06:54:33Z",
      "losses": 350,
      "max_score": 39.0077721461541,
      "measured_at": null,
      "min_score": 15.67108825376102,
      "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": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 462,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.2052004098439,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 4,
      "repaired_rate": 0.2857142857142857,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 25.630385524065343,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 341,
      "capped_draws": 44,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.11219570000000001,
        "mean": 0.0607572625,
        "median": 0.060057275,
        "min": 0.02174195,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.4860581
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.683163448529363,
      "contributing_entrants": null,
      "distinct_rated_opponents": 171,
      "draws": 101,
      "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": "2026-08-05T03:50:20Z",
      "losses": 347,
      "max_score": 40.06000231216052,
      "measured_at": null,
      "min_score": 13.030258973366303,
      "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": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 341,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.6834766789484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 25.503339487650393,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 181
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 677,
      "capped_draws": 28,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0154064,
        "mean": 0.00874386,
        "median": 0.0064215999999999995,
        "min": 0.00524064,
        "recorded_attempt_count": 13,
        "run_count": 9,
        "total": 0.08145696000000001
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 27.21481384964496,
      "contributing_entrants": null,
      "distinct_rated_opponents": 333,
      "draws": 224,
      "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": "2026-08-05T03:19:33Z",
      "losses": 299,
      "max_score": 47.34237964243975,
      "measured_at": null,
      "min_score": 10.523618948427423,
      "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": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 675,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.117531201974,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 24.591360322408136,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 152
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 516,
      "capped_draws": 57,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.09705768000000001,
        "mean": 0.0730637925,
        "median": 0.07051098,
        "min": 0.05225028,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.58451034
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 24.860989928116304,
      "contributing_entrants": null,
      "distinct_rated_opponents": 258,
      "draws": 292,
      "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": "2026-08-05T05:18:47Z",
      "losses": 401,
      "max_score": 46.776416361264104,
      "measured_at": null,
      "min_score": 5.922992138645202,
      "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": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 516,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.3287371284284,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 7,
      "repaired_rate": 0.875,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 24.04475913093154,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 181
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 448,
      "capped_draws": 62,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.0032939400000000004,
        "mean": 0.0016413085000000001,
        "median": 0.0014119655,
        "min": 0.00045831,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.013130468
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 24.79487793327039,
      "contributing_entrants": null,
      "distinct_rated_opponents": 224,
      "draws": 160,
      "entry_count": 14,
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:57:15Z",
      "losses": 349,
      "max_score": 41.569177511800305,
      "measured_at": null,
      "min_score": 9.425383107713568,
      "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": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 448,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.9808781548832,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 23.980817711208037,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 424,
      "capped_draws": 57,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.302804525,
        "mean": 0.259828169375,
        "median": 0.2529231275,
        "min": 0.22308452,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 4.15725071
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 26.89883327152712,
      "contributing_entrants": null,
      "distinct_rated_opponents": 210,
      "draws": 214,
      "entry_count": 18,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:37:42Z",
      "losses": 352,
      "max_score": 50.38530962978662,
      "measured_at": null,
      "min_score": 14.327060935420919,
      "model_code_failure_rate": 0.4375,
      "model_code_failures": 7,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.5625,
      "provider": "Other",
      "provider_key": "other",
      "rank": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 420,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.0307866527764,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 23.295072945304565,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 140
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 575,
      "capped_draws": 81,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.0456916,
        "mean": 0.031545040625,
        "median": 0.035551075,
        "min": 0.01864685,
        "recorded_attempt_count": 35,
        "run_count": 16,
        "total": 0.50472065
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 26.51417335977282,
      "contributing_entrants": null,
      "distinct_rated_opponents": 288,
      "draws": 441,
      "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": "2026-08-05T04:29:54Z",
      "losses": 403,
      "max_score": 38.91324033511728,
      "measured_at": null,
      "min_score": 16.419946190834704,
      "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": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 575,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.9192387904093,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 22.96194768990786,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 329,
      "capped_draws": 36,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0422995,
        "mean": 0.027492531250000004,
        "median": 0.025548,
        "min": 0.0204145,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.21994025
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 25.333116741442588,
      "contributing_entrants": null,
      "distinct_rated_opponents": 165,
      "draws": 169,
      "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": "2026-08-05T05:05:18Z",
      "losses": 321,
      "max_score": 38.95277949062936,
      "measured_at": null,
      "min_score": 16.34618234965383,
      "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": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 329,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.4549379222972,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 22.524679946709842,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 5,
      "attempted_matches": 344,
      "capped_draws": 11,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.13491350000000002,
        "mean": 0.10247140625000001,
        "median": 0.113468875,
        "min": 0.061553000000000004,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.81977125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 23.578339590965374,
      "contributing_entrants": null,
      "distinct_rated_opponents": 172,
      "draws": 71,
      "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": "2026-08-05T05:35:20Z",
      "losses": 362,
      "max_score": 39.79378137592323,
      "measured_at": null,
      "min_score": 3.5186261065286026,
      "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": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.4805040077238,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 20.964437908759642,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 8,
      "attempted_matches": 899,
      "capped_draws": 141,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.038815,
        "mean": 0.02196775,
        "median": 0.0196975,
        "min": 0.016152,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.17574200000000004
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 19.914859222537768,
      "contributing_entrants": null,
      "distinct_rated_opponents": 442,
      "draws": 376,
      "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": "2026-08-05T05:41:40Z",
      "losses": 416,
      "max_score": 36.47520283021661,
      "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": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 893,
      "rating_method": "sequential_elo",
      "raw_elo": 1283.7887205375928,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 19.914859222537768,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 3,
      "wins": 101
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.73533,
        "mean": 0.5886581249999999,
        "median": 0.58241,
        "min": 0.410635,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.709265
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 45.32052335101066,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 221,
      "entry_count": 7,
      "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": "2026-07-31T20:22:43Z",
      "losses": 215,
      "max_score": 67.17363802127772,
      "measured_at": null,
      "min_score": 21.14612832512107,
      "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": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.0438465023874,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "highest",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "highest",
        "reasoning_bucket_label": "Intensive",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "reasoning_setting": "highest",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 45.32052335101066,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 224
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 1498,
      "capped_draws": 366,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 749,
      "draws": 584,
      "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": "2026-07-31T03:35:05Z",
      "losses": 411,
      "max_score": 78.66120174874919,
      "measured_at": null,
      "min_score": 16.341761309376864,
      "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": 1497,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.9837791014288,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 42.74392751708085,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 502
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "capped_draws": 30,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 1,
        "cost_basis_counts": {
          "estimated": 1,
          "local_standard_estimate": 1
        },
        "evidence_basis": "Mixed: Recorded attempt + Standard list-price estimate",
        "max": 0.0023425,
        "mean": 0.0023425,
        "median": 0.0023425,
        "min": 0.0023425,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 1,
          "boardgame-list-prices-2026-07-30": 1
        },
        "recorded_attempt_count": 1,
        "run_count": 1,
        "token_priced_attempt_count": 1,
        "total": 0.0023425
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": 39.478292990152276,
      "contributing_entrants": null,
      "distinct_rated_opponents": 49,
      "draws": 30,
      "entry_count": 1,
      "failed_game_aliases": [],
      "first_pass_admitted": 1,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:27:30Z",
      "losses": 32,
      "max_score": 39.478292990152276,
      "measured_at": null,
      "min_score": 39.478292990152276,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.1194224909668,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Reasoning field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 39.478292990152276,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": 2578,
      "capped_draws": 166,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1289,
      "draws": 757,
      "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": "2026-07-31T20:23:06Z",
      "losses": 946,
      "max_score": 54.257859859863686,
      "measured_at": null,
      "min_score": 17.84653261324441,
      "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": 2578,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.6866641670401,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.46013834265657,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 875
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 642,
      "capped_draws": 119,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 321,
      "draws": 228,
      "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": "2026-07-31T03:28:04Z",
      "losses": 254,
      "max_score": 53.4061534092432,
      "measured_at": null,
      "min_score": 12.693314222369741,
      "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": 642,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.9395847805426,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 32.9209508641027,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 240,
      "capped_draws": 49,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.03772852,
        "mean": 0.024905897500000003,
        "median": 0.026095300000000002,
        "min": 0.00984735,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.19924718
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.94089777477116,
      "contributing_entrants": null,
      "distinct_rated_opponents": 118,
      "draws": 67,
      "entry_count": 8,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:57:11Z",
      "losses": 155,
      "max_score": 53.50967288140359,
      "measured_at": null,
      "min_score": 23.170311606444997,
      "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": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.9332382654093,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 31.063468515058986,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 132
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1308,
      "capped_draws": 237,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 654,
      "draws": 476,
      "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": "2026-07-31T20:22:51Z",
      "losses": 515,
      "max_score": 45.51671696216456,
      "measured_at": null,
      "min_score": 18.666770219098307,
      "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": 1308,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.207774914172,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 30.904388993301325,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 317
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 462,
      "capped_draws": 151,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 231,
      "draws": 302,
      "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": "2026-07-31T20:22:54Z",
      "losses": 102,
      "max_score": 55.431385487557364,
      "measured_at": null,
      "min_score": 18.203309021107163,
      "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": 462,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.070285804948,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 30.680639185909847,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 6,
      "attempted_matches": 452,
      "capped_draws": 56,
      "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": 31.851300693764955,
      "contributing_entrants": null,
      "distinct_rated_opponents": 226,
      "draws": 239,
      "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": "2026-08-05T05:19:01Z",
      "losses": 300,
      "max_score": 45.91779335384322,
      "measured_at": null,
      "min_score": 19.660787526239893,
      "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": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 452,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.6650946740144,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "enabled",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 29.64097519433974,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 227
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 486,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0711619,
        "mean": 0.039345212500000004,
        "median": 0.033877925,
        "min": 0.02387735,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.3147617
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.82089217872514,
      "contributing_entrants": null,
      "distinct_rated_opponents": 243,
      "draws": 183,
      "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": "2026-08-05T05:11:10Z",
      "losses": 186,
      "max_score": 47.50855231655898,
      "measured_at": null,
      "min_score": 23.408407905328904,
      "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": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.0887334584736,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 29.280763409026072,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 486,
      "capped_draws": 34,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.038769960000000006,
        "mean": 0.023744302225,
        "median": 0.0230069837,
        "min": 0.0074361952000000005,
        "recorded_attempt_count": 20,
        "run_count": 9,
        "total": 0.21411433159999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 29.637863783069538,
      "contributing_entrants": null,
      "distinct_rated_opponents": 243,
      "draws": 408,
      "entry_count": 16,
      "failed_game_aliases": [
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T03:36:31Z",
      "losses": 315,
      "max_score": 47.54371771982972,
      "measured_at": null,
      "min_score": 13.117033955210568,
      "model_code_failure_rate": 0.2222222222222222,
      "model_code_failures": 2,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.7777777777777778,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.4993312165873,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 7,
      "repaired_rate": 0.7777777777777778,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 27.83304875218882,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 177
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 228,
      "capped_draws": 74,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 8,
          "local_standard_estimate": 13
        },
        "evidence_basis": "Mixed: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.17217,
        "mean": 0.11039474999999999,
        "median": 0.10846,
        "min": 0.07562,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 13,
          "boardgame-list-prices-2026-07-30": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "token_priced_attempt_count": 13,
        "total": 0.8831579999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.47551028903298,
      "contributing_entrants": null,
      "distinct_rated_opponents": 114,
      "draws": 123,
      "entry_count": 8,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:08Z",
      "losses": 160,
      "max_score": 45.42172085598957,
      "measured_at": null,
      "min_score": 24.48313253075837,
      "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": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.7538901877429,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 27.308540185582956,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 800,
      "capped_draws": 119,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 36
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.215758025,
        "mean": 0.16162675,
        "median": 0.1594081875,
        "min": 0.098579625,
        "recorded_attempt_count": 36,
        "run_count": 16,
        "total": 2.5860279999999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 32.49225562048957,
      "contributing_entrants": null,
      "distinct_rated_opponents": 394,
      "draws": 360,
      "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": "2026-08-05T04:41:06Z",
      "losses": 241,
      "max_score": 59.67122908962842,
      "measured_at": null,
      "min_score": 17.38109358780758,
      "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": 800,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.6737316040624,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 26.42557071449074,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 1582,
      "capped_draws": 448,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 40
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 40,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 29.182224069171387,
      "contributing_entrants": null,
      "distinct_rated_opponents": 636,
      "draws": 825,
      "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": "2026-08-05T05:41:59Z",
      "losses": 510,
      "max_score": 38.9946317420071,
      "measured_at": null,
      "min_score": 17.149445622957767,
      "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": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1578,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.254695962745,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "none",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 25.94707410067487,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 243
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 656,
      "capped_draws": 232,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 30
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 30,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 34.26459574235255,
      "contributing_entrants": null,
      "distinct_rated_opponents": 303,
      "draws": 232,
      "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": "2026-08-05T05:16:56Z",
      "losses": 310,
      "max_score": 27.82104904701147,
      "measured_at": null,
      "min_score": 22.417196747929975,
      "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": 652,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.6116229817628,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "none",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 25.618760741182353,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 110
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 534,
      "capped_draws": 120,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.06200699999999999,
        "mean": 0.042994687499999996,
        "median": 0.0423105,
        "min": 0.0223935,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.34395749999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.20167797369913,
      "contributing_entrants": null,
      "distinct_rated_opponents": 248,
      "draws": 130,
      "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": "2026-08-05T05:02:41Z",
      "losses": 217,
      "max_score": 37.07858798158563,
      "measured_at": null,
      "min_score": 22.730135675874582,
      "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": 499,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.7939790261225,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 25.396482742730665,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 35,
      "wins": 152
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 298,
      "capped_draws": 9,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 52
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 52,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": 31.790674402680526,
      "contributing_entrants": null,
      "distinct_rated_opponents": 146,
      "draws": 147,
      "entry_count": 12,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.06666666666666667,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:56:13Z",
      "losses": 255,
      "max_score": 43.52220457729294,
      "measured_at": null,
      "min_score": 11.744571555937974,
      "model_code_failure_rate": 0.6,
      "model_code_failures": 9,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": 0.4,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.2635012770018,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "enabled",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 5,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 25.282192800215764,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 6,
      "attempted_matches": 491,
      "capped_draws": 78,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 10,
        "max": 0.11839474,
        "mean": 0.07845433000000002,
        "median": 0.08046371000000001,
        "min": 0.036046930000000005,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 1.2552692799999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 31.81970419489655,
      "contributing_entrants": null,
      "distinct_rated_opponents": 246,
      "draws": 131,
      "entry_count": 6,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:35:25Z",
      "losses": 235,
      "max_score": 58.14658525183732,
      "measured_at": null,
      "min_score": 18.369589094882354,
      "model_code_failure_rate": 0.625,
      "model_code_failures": 10,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.375,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 491,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.3895766010774,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 24.900264188962943,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 260,
      "capped_draws": 7,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.3927285,
        "mean": 0.1902770625,
        "median": 0.16804049999999998,
        "min": 0.08751,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 1.914945
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 21.467686926657944,
      "contributing_entrants": null,
      "distinct_rated_opponents": 130,
      "draws": 29,
      "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": "2026-08-05T04:22:40Z",
      "losses": 332,
      "max_score": 28.85019218818374,
      "measured_at": null,
      "min_score": 15.89051825604416,
      "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": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1236.2259394503305,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 17.528292976043055,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 472,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 236,
      "draws": 112,
      "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": "2026-07-31T03:34:49Z",
      "losses": 267,
      "max_score": 41.19784660229971,
      "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": 472,
      "rating_method": "sequential_elo",
      "raw_elo": 1228.2514306279427,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 17.319128239553702,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:35:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 2074.1985502899956,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 2049.195935972635,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 97.55488190852645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-03T20:24:28Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1953.4185734322302,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 88.04000833669701,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 2,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:34:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1863.9196141834548,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 79.75919518016714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:28:48Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1854.3786077597374,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 78.7550562000012,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:29:24Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1847.5791986207955,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 78.1799426050759,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 36,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 36,
      "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": "2026-08-05T02:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.4305585121388,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 72.50601879226893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 22,
      "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": "2026-08-05T05:08:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1787.0910986805159,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 72.251918530255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": "2026-08-03T18:12:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1771.292271328763,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 70.43804280002986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 2,
      "wins": 74
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 284,
      "capped_draws": 123,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 138,
      "draws": 123,
      "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": "2026-08-05T05:16:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 283,
      "rating_method": "sequential_elo",
      "raw_elo": 1743.5487349270413,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 68.29057346028767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1741.6169869231062,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 67.86856369283086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.8539498938124765,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 99,
      "draws": 53,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1744.3715807356245,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 67.70990700393389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.678927433339865,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-03T16:57:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1726.1208318729848,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 66.0359053103189,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 2,
      "wins": 57
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 180,
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 90,
      "draws": 57,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1732.2042579092843,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 65.44532137869037,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.75915957037753,
      "unilateral_faults": 0,
      "wins": 223
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-03T16:33:33Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1716.9606343725054,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 65.2569227596586,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 2,
      "wins": 66
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 290,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 141,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-08-05T03:52:05Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1715.840502074611,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 64.77698597319846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.948489198165475,
      "unilateral_faults": 4,
      "wins": 177
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T03:42:41Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1682.8738949315364,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 62.31323923781224,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 148,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-08-03T14:42:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1684.77832627723,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 61.3843149316053,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.000430913942129,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-05T00:23:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1666.6223623937797,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 60.58028362371113,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 78,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1647.795835483077,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.87147462359901,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "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": 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": 50,
      "max_score": null,
      "measured_at": "2026-08-05T05:28:30Z",
      "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": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1643.003852096852,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.53306464293001,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-07-31T02:50:24Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.9941068004882,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.377814269152495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 13,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T02:29:24Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.6929233650376,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.34870578570014,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1615.7106919093821,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 55.79662342229386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 144,
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 72,
      "draws": 36,
      "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": "2026-08-05T05:37:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.8022570539633,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 55.1044008888968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.752631729955272,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-03T13:20:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.7467039236506,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.57176981147765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-07-31T03:24:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.3217926636212,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.814684949492396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T03:05:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.0420650084584,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.78600839000461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "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": "2026-08-05T05:28:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1600.214154182145,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.73002467422387,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.16054548991772,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-07-31T02:53:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.9048927563001,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.303844169868434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "capped_draws": 110,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 110,
      "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": "2026-08-05T05:09:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.0891855735679,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.11478815980904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-08-03T05:37:21Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1566.3794692670535,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.86269605014598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-08-05T04:26:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 139,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.2246913986785,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.447789575371836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.2174621120816,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.2908922032663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 83,
      "draws": 123,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.567868491681,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.12110302067223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.59559994608984,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-07-31T02:07:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.707369380218,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.77193143521104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 234,
      "capped_draws": 106,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 106,
      "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": "2026-08-05T05:37:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.222833880484,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.76771663674732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.250945381480301,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 170,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 85,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-08-05T05:29:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.3675251085415,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.24502914491117,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.35967662941084,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-08-03T09:57:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.3642738682056,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.08179953707419,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 50
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 284,
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 138,
      "draws": 64,
      "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": 130,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.0320223634517,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.88673329517897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 53,
      "draws": 92,
      "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": "2026-08-05T05:11:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.028184936769,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.17182865923943,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.815914049854921,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-08-03T09:49:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.3045165513727,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.4326698055027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 160,
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 80,
      "draws": 115,
      "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": "2026-08-05T05:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.041221974691,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.199740947921946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.654864507219585,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 386,
      "capped_draws": 88,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 192,
      "draws": 88,
      "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": 163,
      "max_score": null,
      "measured_at": "2026-08-05T01:58:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 386,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.0186160606256,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.07384132839297,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9009167740720869,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-08-03T14:22:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.4090782162627,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.31034547609485,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-03T14:29:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.9159537242554,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.24590085260889,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 64,
      "draws": 60,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-05T05:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.1427938732331,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.04679801633584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.3772661551121,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 212,
      "capped_draws": 58,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 106,
      "draws": 58,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.445425050893,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.286286758943646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.622039417435602,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 86,
      "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": "2026-08-05T05:02:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.9162067080504,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.2640459642207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "capped_draws": 128,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 117,
      "draws": 128,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-08-05T03:42:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.924403802806,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.20358864197766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.042462425705284,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-08-04T20:42:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.891033713489,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.86454300140991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.85345304153558,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T05:35:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.674483808534,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.66078657358321,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 42.71808248423493,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 13,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-03T12:31:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.5108403714787,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.55026889308681,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 37,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.6894964558528,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.47617782039243,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.12451556018153,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T03:13:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.448626577189,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.22577138332814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 94,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 47,
      "draws": 57,
      "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": "2026-08-05T05:26:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.1741194955482,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.043380004909636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.57795513865966,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-04T22:07:16Z",
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.4307170357656,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.791267003138834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 354,
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 175,
      "draws": 43,
      "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": 170,
      "max_score": null,
      "measured_at": "2026-08-04T23:06:51Z",
      "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": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.3329076565353,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.290634444481384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.533796253208408,
      "unilateral_faults": 4,
      "wins": 137
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.3441495353725,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.24489520124794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-03T14:21:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.9647599651043,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.027558696955204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 56,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T02:21:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.9213024915678,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.72079315957007,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-08-05T04:27:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.7795894298745,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.50826721476022,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T05:27:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.1194224909668,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Reasoning field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.478292990152276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-08-05T04:12:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.4577652758578,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.175972926108116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 396,
      "capped_draws": 61,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 198,
      "draws": 61,
      "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": 178,
      "max_score": null,
      "measured_at": "2026-07-31T03:20:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.6405250902899,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.064171182767296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.259380609588918,
      "unilateral_faults": 0,
      "wins": 157
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-05T03:44:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 26,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.5450833553969,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.0077721461541,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.36952453316905,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 366,
      "capped_draws": 114,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 147,
      "draws": 114,
      "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": 139,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.404832296831,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "none",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.9946317420071,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.8654932136196,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.748929094306256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 246,
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 121,
      "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": 120,
      "max_score": null,
      "measured_at": "2026-08-05T04:13:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.2225647130356,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.87228212800732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.1524206416837046,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "capped_draws": 98,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 98,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-07-31T02:06:19Z",
      "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": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.431436730129,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.852645783461874,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.417480511718784,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.8116737375058,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.54208643626219,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 55,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-07-31T03:18:50Z",
      "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": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0411623944224,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.957906696826875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 278,
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 133,
      "draws": 92,
      "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": 103,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:00Z",
      "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": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.3980802647104,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.772634831663424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-07-31T02:06:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.2312169344568,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.09710437506328,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.806447728429966,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 500,
      "capped_draws": 143,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 243,
      "draws": 143,
      "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": 216,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:00Z",
      "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": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 494,
      "rating_method": "sequential_elo",
      "raw_elo": 1400.1087975800988,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.869164176499254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.2807380098319099,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 50,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.785287112545,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.546723164957854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.367480145108665,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 9,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T05:29:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.0011543444123,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.26480003454013,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T05:29:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.4793311113017,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.84315271799331,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.8830041946885,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.37658083021708,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.05751454423861,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "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": 53,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-07-31T03:29:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.4724211227056,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "highest",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "highest",
        "reasoning_bucket_label": "Intensive",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "reasoning_setting": "highest",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.023466950256804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 129,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.8251838934389,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.086613675695194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.10290096535146454,
      "unilateral_faults": 35,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-04T23:49:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.949051352309,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.520204387389295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.0482856713095,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.278226848010597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 24
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 374,
      "capped_draws": 110,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 185,
      "draws": 110,
      "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": 172,
      "max_score": null,
      "measured_at": "2026-08-05T05:15:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 374,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.0336204181292,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.269988200342766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.1643552942737934,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.834157637065,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.947576637723415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.029700787957108,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 20,
      "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": "2026-08-05T05:37:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.7856369791552,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.54179636147906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.5548143433798,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.248133482989893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.16054548991772,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-08-05T02:21:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1324.6039580133202,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.1854385334171,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.032850381472425,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-05T04:11:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1307.5635018079774,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.756034767008668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T05:35:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.2033465124364,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "enabled",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.615070134982144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 36,
      "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": "2026-08-05T05:11:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.0654330664993,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.836164490490482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.06074898572802,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-05T01:59:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 121,
      "rating_method": "sequential_elo",
      "raw_elo": 1294.2112404069253,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.602289135184463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.5178730212592662,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 274,
      "capped_draws": 116,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 129,
      "draws": 116,
      "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": 128,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1269.590378771029,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "none",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.417196747929975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.6667408666858066,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 244,
      "capped_draws": 79,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "draws": 79,
      "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": 137,
      "max_score": null,
      "measured_at": "2026-08-05T04:13:36Z",
      "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": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 243,
      "rating_method": "sequential_elo",
      "raw_elo": 1263.7243618026978,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.661903263791142,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.4392325850739818,
      "unilateral_faults": 1,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-07-31T03:20:56Z",
      "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": 95,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.9886564398028,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.203309021107163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 278,
      "capped_draws": 104,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 133,
      "draws": 104,
      "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": "2026-08-05T05:09:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 96,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 277,
      "rating_method": "sequential_elo",
      "raw_elo": 1223.4085617983565,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.986293369286603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 97,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1219.0922738248978,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 15.89051825604416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 17
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 442,
      "capped_draws": 82,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 219,
      "draws": 82,
      "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": 284,
      "max_score": null,
      "measured_at": "2026-08-05T03:22:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 98,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 438,
      "rating_method": "sequential_elo",
      "raw_elo": 1202.111678705965,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 15.510539068363032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.983045749013221,
      "unilateral_faults": 4,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-07-31T03:26:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 99,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1181.758735531149,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 13.34873652645807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:35:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 100,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1191.341446805984,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 13.030258973366303,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.599360970396255,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 15,
      "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": "2026-08-05T03:16:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1848.6927283605112,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1762.8973316433855,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 81.91642338098146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:59Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1726.5724128111112,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 74.10763610887963,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 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": 56,
      "draws": 40,
      "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": "2026-08-04T08:44:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.0704845544929,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 73.97689904691619,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-04T02:44:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1693.6055326946102,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 66.6442943191533,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 2,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-03T14:22:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1681.6024352152729,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 64.38340087999147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 230,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 115,
      "draws": 96,
      "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": "2026-08-05T04:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1673.5108063757525,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 63.32315344250023,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.6751283820590555,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-05T01:25:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1641.8435026438312,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.16935098002528,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 66,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1605.236191959549,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.68530133471744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-03T04:42:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.7113348170712,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.52465329657686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:46Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.1451957449874,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.88652077650536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 154,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 77,
      "draws": 100,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T04:14:36Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.0189580640395,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.420195919942806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.24674951880897,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 72,
      "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": "2026-08-05T02:29:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.0360257430739,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.05496996375109,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 40,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-05T04:14:55Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.377695628946,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.09734496097713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.33174221445313,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-08-03T03:26:09Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.4533953211321,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.3636679002474,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "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": 74,
      "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": "2026-08-05T03:05:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.202321522418,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.15647522370581,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-05T01:51:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.7410235438656,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.416670221124697,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 106,
      "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": "2026-08-05T04:33:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.7314778179798,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.58345519069338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "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": 152,
      "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": "2026-08-05T04:06:28Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.44121600246,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.99852516396363,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.19101199758159,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 96,
      "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": "2026-08-04T21:44:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.4800705170592,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.69560465698689,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 90,
      "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": "2026-08-04T22:25:42Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.2979775705355,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.620832892368888,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-03T08:48:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.230475769869,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.43537970074668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 200,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "draws": 165,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:59Z",
      "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": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.187976281611,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.174862159682817,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.00917733558763,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-07-31T01:21:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.7218026454714,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.606196776104223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.926723016124,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.09530085961754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 92,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-03T11:50:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.958195948396,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.8282677671406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 96,
      "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": "2026-08-04T23:30:16Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.6693600787999,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.408407905328904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 92,
      "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": "2026-08-04T23:05:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.9195447594993,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.30438447793437,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 91,
      "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": "2026-08-05T01:03:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.89697802721,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.62500365197257,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 80,
      "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": "2026-08-04T23:04:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.2207038900344,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.482461561801962,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 100,
      "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": "2026-08-03T15:08:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.7598583404967,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.448726851866137,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 314,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 157,
      "draws": 278,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T04:11:58Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.1661517225318,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.192579972734823,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.918254315183693,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 95,
      "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": "2026-08-05T03:21:06Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.2394028782717,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.765095786368434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 306,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 152,
      "draws": 285,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-04T22:55:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.4883162878389,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.737279542205624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.521109022046928,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 204,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 167,
      "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": "2026-08-05T02:23:09Z",
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.3783144201457,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.713702201359574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.523431578963063,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 118,
      "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": "2026-08-05T04:33:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.7815159368622,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.571994896490278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 106,
      "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": "2026-08-05T03:06:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.6685144794933,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.375595771095142,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 197,
      "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": "2026-08-05T00:35:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.3978500172125,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.33030113424673,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.321602512009086,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 99,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.1067750294355,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.259905179055554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 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": 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": 1,
      "max_score": null,
      "measured_at": "2026-07-31T03:31:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.6528733974872,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "highest",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "highest",
        "reasoning_bucket_label": "Intensive",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "reasoning_setting": "highest",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.14612832512107,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 108,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.3687742528214,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.78553102586511,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 114,
      "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": "2026-08-05T04:26:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.8238680319553,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.765351621675194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "draws": 91,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-03T14:21:40Z",
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.386500405246,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.671691142857387,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.21328729190924,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 28,
      "draws": 101,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-03T03:19:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.1598241632423,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.42853187574935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.37199257392821,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "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": 86,
      "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": "2026-08-03T09:30:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.2956909913066,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.419129829006703,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 49,
      "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": "2026-08-05T04:06:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.5534739554275,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.36109221661011,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "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": 91,
      "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": "2026-07-31T03:31:12Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.363551009849,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.22265746079894,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 315,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 152,
      "draws": 246,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-08-05T02:23:13Z",
      "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": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 313,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.6823474356468,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.17228110668475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.04483610793667,
      "unilateral_faults": 2,
      "wins": 17
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 53,
      "draws": 134,
      "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": "2026-08-05T04:06:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.0237227206553,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.09827284833638,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.41045953184991,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 75,
      "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": "2026-07-31T03:32:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.4985994938952,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.047433762857775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "draws": 100,
      "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": "2026-08-04T21:01:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.1566233238045,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.793619316293615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.383326230453278,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "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": 86,
      "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": "2026-08-05T05:26:46Z",
      "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": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.3422066867968,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.738580505271273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 57.19171186957297,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 102,
      "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": "2026-08-05T04:33:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.2460261587667,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.60034070265804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 434,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 216,
      "draws": 398,
      "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": "2026-08-05T04:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 434,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.154753586598,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.59118479048314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.081522477821102,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "draws": 98,
      "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": "2026-08-03T12:16:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.927138599855,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.32369832555091,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.383326230453278,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 142,
      "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": "2026-08-05T04:27:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.0305995079593,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "none",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.08311558138147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 287,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 144,
      "draws": 260,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T02:15:28Z",
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 287,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.1689433354313,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.87263301066557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.110614891733731,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 172,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 86,
      "draws": 148,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.388261077859,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.666770219098307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-05T02:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.4026985942367,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.371420182291875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.6483700277522,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.231928182356505,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.5095838835902065,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "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": 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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:14:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.8544104693906,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.1638721019117,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 54,
      "draws": 179,
      "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": "2026-07-31T03:30:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.4667036618916,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.06787100300602,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.255438351974508,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 256,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 128,
      "draws": 231,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.6639372088994,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.84653261324441,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.06462264614784,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": "2026-08-03T14:15:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.63809611208,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.78870942250549,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 65,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:27:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.4735135903006,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.703162245681458,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.92684787488294,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 86,
      "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": "2026-08-03T07:00:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.0231648557492,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.553436099642553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 98,
      "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": "2026-08-03T04:41:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.9978015411527,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.498660025504904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 93,
      "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": "2026-08-05T04:33:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.554229345278,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.49414607975783,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 81,
      "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": "2026-08-05T02:59:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.39352975317,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.488893388132354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 92,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T04:32:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.370338353978,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.38109358780758,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 39,
      "draws": 144,
      "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": "2026-08-05T04:33:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.2406346349167,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.907630545609305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.3536321005172,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 51,
      "draws": 165,
      "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": "2026-08-04T08:44:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.8733711729035,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.83981461551393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.796733626714996,
      "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": 2,
      "distinct_rated_opponents": 25,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-03T08:04:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.6265901311735,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.793318043756123,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "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": 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": 6,
      "max_score": null,
      "measured_at": "2026-08-03T05:47:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.590051762334,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.591663020618228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 83,
      "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": "2026-07-31T03:32:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.35753048828,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.341761309376864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 52,
      "draws": 124,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T04:27:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.5326509606543,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.238936021776848,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 48.18433039621293,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 21,
      "draws": 117,
      "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": "2026-08-05T04:06:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3113488830672,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 15.67108825376102,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 48.77531126230131,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 22,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 11,
      "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": "2026-08-05T01:26:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 22,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.2658829829716,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 15.558477194480595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 50.636316250694534,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "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": 136,
      "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": "2026-08-05T04:33:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.2464671154166,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 15.356957668247802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.307153450636115,
      "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": 13,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-08-05T04:06:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 26,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.4301694661972,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 14.327060935420919,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 1
    },
    {
      "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": 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": 8,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:22Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.0350810658178,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 13.313054666786927,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:14:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.4555743343753,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 13.096859594916474,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.22199845071155,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "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": 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": 10,
      "max_score": null,
      "measured_at": "2026-08-05T01:19:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.4630623113085,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "enabled",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 11.744571555937974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 42.25107233303306,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "draws": 81,
      "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": "2026-08-03T14:23:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.1938068693948,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 10.34354662706081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 28,
      "draws": 86,
      "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": "2026-08-03T08:16:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.8948469330253,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 9.967521810790636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.829556801099734,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 74,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-04T05:07:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.23350130035,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 6.649465460691646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.430533588759353,
      "unilateral_faults": 2,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 190,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "draws": 8,
      "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": "2026-08-05T04:20:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1904.2815482198878,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 97.66928476084789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.283112930469331,
      "unilateral_faults": 0,
      "wins": 167
    },
    {
      "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": 52,
      "draws": 0,
      "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": "2026-08-03T14:17:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1912.3418465864775,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 97.33599973224807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 111
    },
    {
      "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": 38,
      "draws": 44,
      "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": "2026-08-03T14:08:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.7450741307903,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 68.08895739222693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 31
    },
    {
      "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": 37,
      "draws": 7,
      "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": "2026-08-05T00:16:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1674.9780101817953,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 64.47438248139325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:21:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1637.788138173864,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.14658525183732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 96,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T03:55:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.1421724289517,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.01848820960669,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T06:54:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.2983594055843,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.058616923197214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 105,
      "draws": 39,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.538456140085,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.60139245654345,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.828889084636114,
      "unilateral_faults": 0,
      "wins": 107
    },
    {
      "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": 36,
      "draws": 16,
      "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": "2026-08-04T22:43:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.6282681640967,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.36568330922522,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 16,
      "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": "2026-08-05T01:53:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.797238543221,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.3566269308408,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 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": 6,
      "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": "2026-08-03T14:16:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 26,
      "rating_method": "sequential_elo",
      "raw_elo": 1606.495361338857,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.426383488215265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 64.99642869155205,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 106,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 53,
      "draws": 34,
      "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": "2026-08-04T21:24:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.589788520244,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.1413174012522,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 37.60341101879811,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 89,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-03T14:17:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.5150630244484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.36721779549708,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-07-31T02:50:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.5697459219878,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.51671696216456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 20
    },
    {
      "admitted_plugins": 3,
      "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": 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": 19,
      "max_score": null,
      "measured_at": "2026-08-03T13:45:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.4871568460653,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.919362734240536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 63.08754591278003,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 70,
      "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": "2026-08-05T02:50:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.2621082602757,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.85859288843461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 42,
      "draws": 60,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.2009489848747,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.18173729841307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.670087811963565,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.6690644495093,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.65724563741933,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.08463570631327,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 41,
      "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": "2026-08-05T05:17:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.1113435198147,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.47234326149914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.5513087187508,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.96266756353682,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 96,
      "draws": 94,
      "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": "2026-08-05T05:23:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.0195089700449,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.88653195721722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 282,
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 141,
      "draws": 130,
      "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": 77,
      "max_score": null,
      "measured_at": "2026-08-05T06:54:33Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.3805631851592,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.52750766968367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.587895361038879,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 55,
      "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": "2026-08-05T04:02:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.0791075326886,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.825908860305795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 78,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 39,
      "draws": 56,
      "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": "2026-08-05T06:55:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.186271761107,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.78232130318044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.35134825637578,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 42,
      "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": "2026-08-03T13:39:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.6386415291488,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.7417856969161,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 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": 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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.0744357797557,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.420981492242916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "draws": 65,
      "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": "2026-08-03T12:18:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.528494060152,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.26992541010253,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 13
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 274,
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 129,
      "draws": 101,
      "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": 98,
      "max_score": null,
      "measured_at": "2026-08-05T04:45:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.5177561237024,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.24190944943468,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.965236003466329,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 302,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 151,
      "draws": 172,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-08-05T04:03:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.4152606481027,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.007466418277744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.884068654918515,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 41,
      "draws": 69,
      "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": "2026-08-05T04:21:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.8677330951837,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.11964378771493,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.951351796455231,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T01:37:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.5833143372236,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.87270762029662,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 33,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T02:45:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.2301237737283,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.6743793289876,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.04200090392808,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 273,
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 137,
      "draws": 143,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 273,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.6051563726742,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.442561303818024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.534824386604422,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 36,
      "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": "2026-08-05T03:55:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.4575917303791,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.871448824939826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 47,
      "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": "2026-08-05T05:24:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.2219053386525,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.47520283021661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 56,
      "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": "2026-08-05T04:11:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.7736263454274,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.95312226500334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 94,
      "draws": 75,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.9147812034898,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.908955370742355,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.311964357860807,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 52,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 25,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T04:45:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.5338748338609,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.67859448493501,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 57.59714166026543,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 51,
      "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": "2026-08-05T05:17:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.459954262159,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.324362595440974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T06:54:28Z",
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.648879874152,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.172389071472274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 48.41064196554048,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 160,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 77,
      "draws": 57,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T04:45:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.742396565601,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.09417723351375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.960415358888525,
      "unilateral_faults": 6,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 50,
      "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": "2026-07-31T02:57:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.620482045245,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.82102759332112,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 34,
      "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": "2026-08-05T02:49:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.96396152062,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.56114839964518,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 180,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 90,
      "draws": 83,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "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": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.0805512513246,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.32865162817713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.817010378902888,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 119,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 60,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 119,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.2197047485586,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.1367649976849,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.666338886355163,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "2026-08-05T05:23:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.1293236265938,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.94223147070685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-03T10:31:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.33064839219,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.94213073013162,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 15
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 204,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 102,
      "draws": 87,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-07-31T03:07:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.6337719916312,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.95596680854231,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.493622478518038,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-04T22:57:18Z",
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.0203867601301,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.8904510243238,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-04T03:30:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.0279417186953,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.829666021771125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 2,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T04:36:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 26,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.0723605102608,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.4038428924734,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 14
    },
    {
      "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": 13,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-04T03:25:30Z",
      "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": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 26,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.6289635368048,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.12774530392546,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 73.70004696062244,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 59,
      "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": "2026-08-05T06:55:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.7211533982504,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.36280463053722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "capped_draws": 3,
      "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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T06:54:33Z",
      "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": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.9321995857717,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.80483322714281,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 35.629606032316254,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 282,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 137,
      "draws": 101,
      "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": 109,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:13Z",
      "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": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.7658989510273,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.687958478700622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.692178568782805,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 69,
      "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": "2026-08-03T11:47:32Z",
      "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": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.1509269893077,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.410317232417285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 15,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-03T13:44:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.1284872075441,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.22692688715613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 35,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-08-03T03:06:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.2409871410878,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.72176486319264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.22199845071155,
      "unilateral_faults": 1,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 50,
      "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": "2026-08-05T06:55:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.5707786523924,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.421961467653944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-03T14:16:49Z",
      "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": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.4866662482673,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.49558535920104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T01:53:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.0451235991713,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.109328607264317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-03T12:01:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.5628668819243,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.045539172534085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.759688346625158,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "draws": 83,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.7986598115863,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.99213047697091,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.251875136730032,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T00:30:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.1218657893382,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.840176236683952,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-07-31T02:59:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.2542607455403,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.603816053425483,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-04T08:55:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.4812698372175,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.26550399898632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.430533588759353,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 53,
      "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": "2026-08-03T15:07:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.1018350385903,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.18896644366903,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 252,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 102,
      "draws": 106,
      "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": 97,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.5273535246738,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "none",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.15995528948202,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.6219524331384951,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-04T22:43:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.7892085139326,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.061882688196544,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 28,
      "draws": 41,
      "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": "2026-08-04T20:26:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.2594736718875,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.457791809431576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.9177814856242,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 54,
      "draws": 69,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-08-05T04:45:00Z",
      "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": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.2109374982958,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.850957987441,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.655454738281755,
      "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": 2,
      "distinct_rated_opponents": 21,
      "draws": 36,
      "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": "2026-08-05T04:21:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.16540861595,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "enabled",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.815666165261234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.406681034422945,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-04T22:38:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.8681392042768,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.2055412078098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-04T22:56:54Z",
      "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": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1343.0197207211138,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.71770471751947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1883.5568183188263,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 87,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:36Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1772.8326811225836,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 79.44376401396596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.3360960868538,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.68991920919109,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 53,
      "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": "2026-08-05T04:05:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1649.8433166463897,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.064818144611,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.1138216200993,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.093874217143885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:03:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.4398535001199,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.695876476828644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 67,
      "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": "2026-08-05T05:32:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.8397934807497,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.45429450824968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 250,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 125,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:34Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.5843980718105,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.570204853782045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.7945925104007445,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 48,
      "draws": 61,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-05T06:57:15Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.8218153276666,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.8242290880386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.03600868187805,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.9423799806716,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.546679444120066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 65,
      "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": "2026-07-31T02:32:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.8964765379387,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.553899944193034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T05:04:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.1647476691362,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.9332689282377,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 240,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.6697759458552,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.830660376507744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.72318795104911,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 234,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 117,
      "draws": 150,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T04:04:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.0156907933451,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.808585407262754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.3097625762757357,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "draws": 63,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.629970640442,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.7928749336898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.187341079842824,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 350,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 175,
      "draws": 231,
      "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": "2026-08-05T05:11:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.0267619373572,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.44018940023784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.39663743638847,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 70,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude 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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.800435260969,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.255041035684194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 53,
      "draws": 46,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-08-05T04:52:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.013755601416,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.62630808796079,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.54930561887425,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 85,
      "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": "2026-08-05T05:11:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.4642993530238,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.99073310635768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": "2026-08-05T02:20:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.471964521424,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.626895289462276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 86,
      "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": "2026-08-05T05:33:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.5967389400641,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.93334802211057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 60,
      "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": "2026-08-05T03:48:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.5637786917036,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.4004936024422,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 72,
      "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": "2026-08-05T03:15:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.3585869717513,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.64521003475906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T02:15:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.6000534256289,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.62557494988089,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 252,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 123,
      "draws": 179,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.4132564019528,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.28968021864736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.337553133978721,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 100,
      "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": "2026-08-05T03:15:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.7853187158266,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.82673440407081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 100,
      "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": "2026-08-05T05:03:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.241305078549,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.39551820970374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 74,
      "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": "2026-08-05T04:03:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.187494103844,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.354804347535634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 193,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 96,
      "draws": 155,
      "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": "2026-08-05T05:11:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 189,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.0215300759746,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.75108194933963,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.844126329515209,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 81,
      "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": "2026-08-05T04:04:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.14488539432,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.685761656722633,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 55,
      "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": "2026-08-05T04:29:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.0415678282136,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.676324126516743,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 98,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 49,
      "draws": 115,
      "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": "2026-08-05T06:56:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.5867928352518,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.549162054857096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.961000041312673,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 130,
      "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": "2026-08-05T05:33:30Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.684673413206,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "none",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.91354977203183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 64,
      "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": "2026-07-31T02:30:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.923140293816,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.378827209357606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-08-04T23:35:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.6015655750139,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.225424673213766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.9358300464557,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.207725737710934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 350,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 175,
      "draws": 263,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-07-31T02:43:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.0847759258468,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.02813630675977,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.456975972465711,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 84,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.788961263713,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.724504900603456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "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": 158,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T00:15:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 119,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.1339801476183,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.69438395580862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.849551007159698,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:45Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.097654712804,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.555732530370754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 27,
      "draws": 85,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.5332726354854,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.318855181547832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.97152085681538,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 93,
      "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": "2026-08-04T03:46:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.9113112622058,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.209493257271063,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 2,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 64,
      "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": "2026-07-31T02:31:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.3395528223577,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.200565710939646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 84,
      "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": "2026-08-05T01:02:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.5395240183984,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.65944702485429,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 79,
      "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": "2026-08-05T03:47:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.0901092415422,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.334173890509387,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 46,
      "draws": 110,
      "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": "2026-08-05T06:56:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.5521886227466,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.207540924358696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 37.757061895277,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 170,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 85,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.2138469305178,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.156444808513356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.19101199758159,
      "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": 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": 4,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.810743470332,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.944136333040866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 208,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 102,
      "draws": 153,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T02:20:00Z",
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.9735934356604,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.59744302717278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 182,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 91,
      "draws": 148,
      "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": "2026-07-31T02:31:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.5180903312562,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.575209497586215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.380913286308589,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 81,
      "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": "2026-08-04T23:28:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.7609209020502,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.455964717492304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 107,
      "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": "2026-08-05T03:15:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.5540638545763,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.261376379497502,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 101,
      "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": "2026-08-05T02:13:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.005582006335,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.076279916551638,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "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": 79,
      "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": "2026-08-05T05:03:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.7851670523426,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.353579719814093,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.747146215609725,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 218,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 107,
      "draws": 153,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-08-05T05:32:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.2060981772852,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.004687671221845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.960122029721176,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 20,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.8549762856173,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.77246145445514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.393187298490844,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "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": 73,
      "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": "2026-07-31T01:54:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.0634628191417,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "highest",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "highest",
        "reasoning_bucket_label": "Intensive",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "reasoning_setting": "highest",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.644301789874174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T04:04:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.1287926439377,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.500503430901084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.63492938218381,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 220,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 105,
      "draws": 138,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-08-05T05:05:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.168428759483,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.496322085294256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.713678840118715,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 99,
      "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": "2026-08-05T03:14:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.9697022578662,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.459132843149533,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.7100792380625,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.412668235568347,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 211,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 106,
      "draws": 158,
      "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": "2026-08-05T05:04:07Z",
      "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": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 211,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.161344400508,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.126773678453485,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.801966733820217,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.62788625461,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.042469828678968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 79,
      "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": "2026-08-03T14:28:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.8284045199428,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.033306918921557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 81,
      "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": "2026-08-05T05:32:54Z",
      "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": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.8750459371463,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.006731116118797,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 31,
      "draws": 132,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.4924064050508,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.82534266256079,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.30505935463012,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 85,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.5159546573475,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.604745440205885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "draws": 99,
      "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": "2026-08-05T03:57:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.3940832357684,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.474165233139676,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.63492938218381,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-04T02:50:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.6340912382486,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.21197020273949,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.26622208392424,
      "unilateral_faults": 2,
      "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": 2,
      "distinct_rated_opponents": 35,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T01:16:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.2016771791557,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.02481878600439,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.032850381472425,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 342,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 169,
      "draws": 256,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:34Z",
      "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": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.132843310276,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.9977782784657,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.8856705632567614,
      "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": 2,
      "distinct_rated_opponents": 29,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.7663160414843,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.71090838679187,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 49.43113400428921,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "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": 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": 11,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.9162000332021,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.676956043399027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 53,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.9882412604513,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.47104312016287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.38386256637516,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-05T05:05:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.1431895503845,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.189651778222867,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.042905911570074,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 60,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-07-31T02:43:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.0838971738003,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.132535136739396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.61771759515517,
      "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": 2,
      "distinct_rated_opponents": 30,
      "draws": 85,
      "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": "2026-08-05T05:05:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.9539606604203,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.115823492649717,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.806447728429966,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "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": 104,
      "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": "2026-08-05T02:15:10Z",
      "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": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.701938811887,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "enabled",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.44671790523425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.664741204687253,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 306,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 152,
      "draws": 247,
      "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": "2026-08-05T05:33:30Z",
      "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": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.841790346759,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.412909336833845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.575689184935122,
      "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": 2,
      "distinct_rated_opponents": 30,
      "draws": 84,
      "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": "2026-08-05T05:05:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.9173614142396,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.40588512859002,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "draws": 91,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-05T01:17:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.6472427180993,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.99855480228331,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.976534673506283,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 144,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 72,
      "draws": 143,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T06:57:05Z",
      "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": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.582785992217,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.785677670777737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.851648028961442,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 218,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 105,
      "draws": 70,
      "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": 96,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:36Z",
      "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": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.466947435084,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.002828160874977,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.9246070243412623,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 35,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T05:04:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.5829391383131,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.855391019353213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.599360970396255,
      "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": 2,
      "distinct_rated_opponents": 30,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.1610541264322,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.326469166627668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.26622208392424,
      "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": 2,
      "distinct_rated_opponents": 28,
      "draws": 74,
      "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": "2026-08-05T06:56:13Z",
      "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": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.8532139778922,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "enabled",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.203835010961818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.48795150977726,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:55Z",
      "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": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.4153901661002,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.01689741998006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.996324165557496,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 80,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.0958174926009,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.419946190834704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.26622208392424,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.493662395028,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 12.006801731616441,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "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": 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": 38,
      "max_score": null,
      "measured_at": "2026-08-05T04:13:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.5024527616583,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 11.592420116905998,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.992031574433888,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "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": 42,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.817538672456,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 11.347553349665287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 49.59614362960207,
      "unilateral_faults": 8,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T06:57:15Z",
      "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": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.6747251558618,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 9.425383107713568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.09288922855442,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": "2026-08-05T00:53:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 2099.7620540108987,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 94.13268706699881,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T00:52:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 2067.6605378147365,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 91.54521731701738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 288,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 144,
      "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": "2026-08-05T04:56:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 2016.6529826130795,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 87.54961526135239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 262
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-03T14:57:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 2013.0080873189577,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 86.33840661001909,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.468842775200363,
      "unilateral_faults": 0,
      "wins": 140
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T01:40:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1977.5155798619357,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 84.01665989467725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 266,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 133,
      "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": "2026-08-05T05:35:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1961.7749539008435,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 82.88602996661304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 236
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T01:40:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1882.615074493054,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 76.14344213568862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-03T09:10:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1852.4714723440495,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 73.59018908373541,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 180,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 90,
      "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": "2026-08-05T05:25:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1811.3147558011215,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 69.79149227763016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 126
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T01:40:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1781.323497099848,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 67.68754926078236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 318,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 159,
      "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": "2026-08-05T05:26:36Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1775.7285813884528,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 67.06621443748418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.587275524205726,
      "unilateral_faults": 0,
      "wins": 229
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1763.8599969928403,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 66.26529025688052,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:35:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1723.859615334493,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 63.045401528569364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9885453854133264,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-03T13:20:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1717.0927003529362,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 62.411231853726754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T01:40:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.3815440244537,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 61.05007234863776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:01:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1691.8487318885484,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 60.437208079044204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T05:05:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1717.2211615795206,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 60.18939037750328,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 35.72194732417195,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-04T22:34:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1695.9221727866338,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 59.509667167131056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.339588834282274,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "2026-08-05T02:32:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1654.2910020114755,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.22626896121154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:41:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.4694531265427,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.14727397018848,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:23:04Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.153408374177,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.59451105913189,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:51:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.976425086682,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.10379418968867,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 54,
      "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": "2026-08-05T05:06:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1639.773680061784,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.986630660102286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.36946558518069,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 148,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 74,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:47Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.7605219975048,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.69350786141744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.519493990550963,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "2026-07-31T02:29:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1611.682762884176,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.4061534092432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-08-05T05:13:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.2941355766166,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.07100335059694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.31577533888108,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 44,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.9703793474673,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.061970706152835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.29717474536497,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 236,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 118,
      "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": 88,
      "max_score": null,
      "measured_at": "2026-08-05T00:20:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.3571049572838,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.809153048377176,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.089780903323941,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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": "2026-08-05T03:41:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.5335585643102,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.65682323634443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T00:20:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.5212453673003,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.63127668910358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.6015854557863,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.59419174705676,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.384199623850844,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 99,
      "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": 105,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.0007086934363,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.33642397618402,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.2668860824478045,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:01:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1592.574318717706,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.20111840015675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "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": 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": "2026-07-31T02:29:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.0763597162888,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "highest",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "highest",
        "reasoning_bucket_label": "Intensive",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "reasoning_setting": "highest",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.82932568614319,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "2026-08-05T03:58:47Z",
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1587.0990394515595,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.723957204300376,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 244,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "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": 124,
      "max_score": null,
      "measured_at": "2026-08-05T01:40:45Z",
      "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": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.623648139087,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.802629023107144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.4376202060078436,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-08-03T08:44:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.0681049031327,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.5644545454188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.79936318977655,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:42:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.0136054414809,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.39508357270537,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:40:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.7302568220246,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.38205655158486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 394,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 191,
      "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": 204,
      "max_score": null,
      "measured_at": "2026-08-05T03:58:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 394,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.5375887832508,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.992442092413626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.32378651666526537,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 47,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.6588656258828,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.73802589876419,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.239599789301113,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-05T04:59:59Z",
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.696720232599,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.71671953757412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.857940612168754,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:32:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.7324094191993,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.49884905114305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-08-05T03:58:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.595661388488,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.197008068659926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1566.1873360530612,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.01545827784715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.287101294886725,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 62,
      "max_score": null,
      "measured_at": "2026-08-05T03:49:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.5784583726859,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.80361235858553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 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": 72,
      "max_score": null,
      "measured_at": "2026-08-05T03:00:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.122545035995,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.59284136341126,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.64065622904072,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:49:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.4801116415908,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.50855231655898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:53:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.0016338263567,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.37246936992358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.5598581168831473,
      "unilateral_faults": 0,
      "wins": 121
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T01:37:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.5681458624933,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.34237964243975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 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": 85,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.687707880838,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.911341645144915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.61525389910498,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 78,
      "max_score": null,
      "measured_at": "2026-08-05T05:25:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.7373353693486,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.55395008692883,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:40:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.2916673268228,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.955454000683424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-05T02:08:23Z",
      "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": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.9643907366299,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "enabled",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.91779335384322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.180881873546443,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-05T04:51:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.2714896969158,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.45963078171682,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 60,
      "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": 97,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.0851080733141,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.42181568717994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.554665212036397,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-08-03T10:18:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.2804128851371,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.84698418707792,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.459772198068393,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-03T11:29:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.8798297824787,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.653927467729666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-08-05T01:10:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.5598725581976,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.16059564656367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-03T11:38:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.8535519192562,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.95654254826272,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 238,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 8,
      "distinct_rated_opponents": 119,
      "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": 174,
      "max_score": null,
      "measured_at": "2026-08-05T04:59:59Z",
      "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": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.1809824903353,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.512279064156786,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.26244469819276,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-08-05T04:59:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.7093916476515,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.84220365172713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.51897044633476,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 410,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 205,
      "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": 206,
      "max_score": null,
      "measured_at": "2026-07-31T03:35:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 410,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.4230061325848,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.31485423521351,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.423535000954365,
      "unilateral_faults": 0,
      "wins": 204
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "2026-08-03T11:37:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2207722244411,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.296018158068726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-08-03T10:09:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.5233581127313,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.06000231216052,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 418,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 209,
      "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": 224,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:06Z",
      "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": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 418,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.0659044162278,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.16950375360156,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 194
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 334,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 167,
      "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": 176,
      "max_score": null,
      "measured_at": "2026-08-03T14:20:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.9556199173985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.583428548446186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.4266622086615564,
      "unilateral_faults": 0,
      "wins": 158
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:56:17Z",
      "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": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.9852834380013,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.002182892666326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 60,
      "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": 111,
      "max_score": null,
      "measured_at": "2026-08-05T05:25:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.8691016822452,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.8518501101937,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.341193710595128,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-08-03T12:50:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.595814890767,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.34046965332213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-03T14:20:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.4191254057696,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.26747573047881,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 376,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 188,
      "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": 214,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 376,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.534006668353,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.982306358442266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.0126757293056905,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 496,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 248,
      "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": 294,
      "max_score": null,
      "measured_at": "2026-08-05T04:42:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 496,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.1825662737183,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.68541016863408,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3157835475016277,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-08-04T22:17:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.7528252039147,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.61730356084032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.046738977996931,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 158,
      "max_score": null,
      "measured_at": "2026-08-05T00:09:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.6797930025884,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.48028584036205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.336874464495992,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 242,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 118,
      "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": "2026-08-05T02:16:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.6178552902875,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.450305869169036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.528142200703182,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "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": 20,
      "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": "2026-08-05T05:05:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.2948562490126,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.188022973615546,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.393187298490844,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 61,
      "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": 144,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.1260289908478,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.999553826228972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.838796696547423,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 364,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 182,
      "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": 223,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:55Z",
      "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": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.745838091093,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.727067905022835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.4690985922539064,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 254,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 155,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:55Z",
      "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": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.3191922229553,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.593166509925418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.48567977499789805,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "2026-08-03T11:38:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1337.1021659225844,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.911374561641104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-08-05T03:42:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.0855540317798,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.195666678862878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.717338510322858,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-07-31T03:33:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.0778253765666,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.04003032328393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.05264788810895,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:56:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.945520868201,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.06235888002087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 119,
      "max_score": null,
      "measured_at": "2026-07-31T03:33:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1307.71554307816,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.266873714533958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.815914049854921,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "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": 98,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:25Z",
      "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": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1295.4437942097927,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.78924812766465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 92,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 104,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.6954858769009,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.677731076611366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.98442636283953,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 176,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 88,
      "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": 128,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1283.6228237197265,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.9737881632984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1291.0038555913918,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.543257483194672,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.96298192699785,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "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": 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": "2026-08-04T09:17:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1279.0180447312632,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.956093569257188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.82750658264339,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 360,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 180,
      "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": 262,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 360,
      "rating_method": "sequential_elo",
      "raw_elo": 1238.0288756535647,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.69114574283472,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7169737855478928,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-08-04T21:09:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1234.4309794055496,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.28851435525645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1241.2401742692932,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.668950001695563,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.132502076248564,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 120,
      "max_score": null,
      "measured_at": "2026-08-05T05:06:20Z",
      "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": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1248.8221416706815,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.28831645151227,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.34496024750244,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 128,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 95,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1245.754396970667,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.109036910675474,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 35.2114810203569,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-08-05T02:32:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 96,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1201.3664980516578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.625108861534393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 95,
      "max_score": null,
      "measured_at": "2026-08-05T00:53:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 97,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1177.988284897323,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.34618234965383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.26568574800236,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "2026-08-05T04:55:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 98,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1142.4053752159446,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 14.75877111394388,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 232,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 114,
      "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": 172,
      "max_score": null,
      "measured_at": "2026-08-03T22:34:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 99,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1131.6573902393625,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 13.789037064172394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.880529885641141,
      "unilateral_faults": 4,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 100,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1111.844236303335,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 12.001624306152966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 117,
      "max_score": null,
      "measured_at": "2026-08-04T23:59:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 101,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1050.902463188506,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 5.922992138645202,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.4544298291952,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-03T23:25:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 102,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 966.111945528687,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 2,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-04T23:53:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 2009.1734856604521,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 15,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1968.7663861920653,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 96.50163167645941,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-08-03T14:55:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1955.8803057155433,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 94.87005862041984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T02:29:19Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1905.694154233326,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 90.18024385545019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-05T01:04:28Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1885.1585395368777,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 88.3001049099167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:50Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1868.8044414067544,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 86.64377257189392,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T00:01:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1864.9721170328544,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 86.35067612265574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-04T23:53:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1862.8948429941306,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 86.15355149666183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T02:41:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1851.262045065243,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 85.08346922744767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 168,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T06:54:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1841.5133446168375,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 83.67694797963125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 132
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": "2026-08-05T00:37:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1823.2710278734628,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 82.35863358446323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T00:51:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.5613422611286,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 81.9183167340137,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T03:41:17Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1806.124039833382,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 80.83296452654382,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T01:04:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1791.117462946414,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 79.30739463261588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 89,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-07-31T02:45:11Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1787.4376165902647,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 78.66120174874919,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.957067918206963,
      "unilateral_faults": 0,
      "wins": 107
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 28,
      "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": "2026-08-03T12:25:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1792.51834753957,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 77.86243893295662,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.829556801099734,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 42,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:47Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1787.873868416896,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 76.9153537911332,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": "2026-08-05T00:01:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1764.9290441113433,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 76.82222311841032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": "2026-08-05T03:09:16Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1741.4491229052383,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 74.75879788264669,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 88,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 44,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:18Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1740.0120087892494,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 72.5401989690437,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.30298644536222,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-03T09:48:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1695.989456164501,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 70.28014429931316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-08-04T23:37:14Z",
      "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": 1700.6031514919032,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 69.54336053342072,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.517288899732886,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-08-03T11:04:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1663.2988732348192,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 67.31147896345796,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 217,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:24Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 217,
      "rating_method": "sequential_elo",
      "raw_elo": 1657.1298506300159,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 66.59262070172484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.402236279499051,
      "unilateral_faults": 0,
      "wins": 121
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-08-03T13:30:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1670.792977708839,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 66.50580979104048,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.26622208392424,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-03T07:34:03Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1662.1296966917387,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 66.15885507474644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.007326216468247,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-03T10:50:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": 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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1642.207296864758,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 65.53875120306154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-08-03T11:32:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.6573877546402,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 64.6891432709365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.52648327229861,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 60,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:36Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.6643540912712,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 62.82646209967631,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.571060443119833,
      "unilateral_faults": 0,
      "wins": 128
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T03:41:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.4018687999608,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 61.2479202482627,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "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": 109,
      "max_score": null,
      "measured_at": "2026-08-05T01:53:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.5913398799398,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 60.20667295526242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9885453854133264,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 244,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 115,
      "draws": 18,
      "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": 113,
      "max_score": null,
      "measured_at": "2026-08-05T03:09:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.872562787418,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 59.82214388179885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.4376202060078436,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.5694499676742,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.42525560215735,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.926617622282734,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-03T13:58:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1566.5712031640337,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.99889288812461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-08-05T00:01:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.556641341538,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.81303259089284,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "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": 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": 39,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.3186052823542,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "highest",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "highest",
        "reasoning_bucket_label": "Intensive",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "reasoning_setting": "highest",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.37101372189614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 40,
      "draws": 16,
      "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": "2026-08-05T05:35:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.03231877175,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.92689918058069,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.742063492063494,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 366,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 181,
      "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": 157,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.4143973553253,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.65051046409322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.360347800585077,
      "unilateral_faults": 0,
      "wins": 205
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-03T13:58:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.1182735858504,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.63398289929676,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.9370321371216,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.51235426034554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 64,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-08-05T06:54:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.8482780083127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.503902002777224,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.83387508077879,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 490,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 245,
      "draws": 31,
      "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": 232,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 490,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.721116470262,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.30542073431529,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.4685987893416486,
      "unilateral_faults": 0,
      "wins": 227
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.3048803307256,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.22200846259964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 176,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 88,
      "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": 112,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.7203640226057,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 55.56087546422818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.845848565914157,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "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": 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": 38,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.4105298643044,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 55.431385487557364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 60,
      "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": 98,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.3452760559187,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.57943316939411,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.4772197274317325,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.5251926323524,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.50967288140359,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.621021663051927,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T01:59:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.8036267291184,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.03010894281152,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T06:54:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.508649868163,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.60384576894331,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.6505214838016,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.43242453240839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.38990374359382,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 60,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:18Z",
      "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": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.361759571965,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.32856442995505,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.14703191068986,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.0877615675836,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.38530962978662,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.47940711208657,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-08-03T09:49:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.0649919553914,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.87158633438607,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 326,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 161,
      "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": 168,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.9037775432546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.233162638067576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.098238467332041,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 250,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 123,
      "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": 123,
      "max_score": null,
      "measured_at": "2026-08-05T04:32:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.3729776380346,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.14506340139004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.042462425705284,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 152,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 8,
      "distinct_rated_opponents": 76,
      "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": 140,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:24Z",
      "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": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.1954291728616,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.82771632283495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.22581938124281,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.3666186655798,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.345931211891994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 364,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 182,
      "draws": 25,
      "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": 206,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.7359612918535,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.139430458543245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.390159544298225,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T03:56:30Z",
      "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": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.3657683124545,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.98896150615873,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 35,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-08-05T05:13:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.582517561534,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.976480556909316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.09478634937246,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-08-03T13:58:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.6560155217642,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.187078959151634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-03T09:47:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.139471593564,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.005316505702595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-08-04T23:08:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.2494860259037,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.05907181803922,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-08-03T10:58:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.3978131432787,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.949273557550775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.605642525274,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.569177511800305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.755845925186044,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-07-31T02:02:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.5270623462427,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.19784660229971,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "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": 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": 80,
      "max_score": null,
      "measured_at": "2026-08-03T12:10:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.6428600108695,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.92205480031329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.748827762211599,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.7066706089265,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.82667813491906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 63,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-08-04T23:17:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 63,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.5860385894107,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.91324033511728,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.966247874473638,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T05:20:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.4703196886467,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.608044412593436,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.09174363298229,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 358,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 174,
      "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": 184,
      "max_score": null,
      "measured_at": "2026-08-05T01:52:26Z",
      "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": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 358,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.455342849291,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.586565302093824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.8559527250035135,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-05T00:42:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.9510085269612,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.046844177408595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 135,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": 88,
      "max_score": null,
      "measured_at": "2026-08-04T20:06:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 135,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.5848235187086,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.38276681114314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-05T00:42:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.0460288080308,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.07858798158563,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-08-05T00:01:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1357.7423100535907,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.06130479180287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.805911392508083,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 54,
      "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": 108,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.7633259115487,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.49351604319952,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.06128752274429,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1326.421769500473,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.572024225518824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "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": 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": 85,
      "max_score": null,
      "measured_at": "2026-08-05T04:57:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.3252491367793,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.540674524591545,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.237183532345085,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "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": 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": 86,
      "max_score": null,
      "measured_at": "2026-08-03T13:20:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1324.5664254277772,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.10425107444389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.28737186011545,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "draws": 21,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1333.2717926998414,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.7490542863941,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.84785372359809,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "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": 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": 91,
      "max_score": null,
      "measured_at": "2026-08-05T01:46:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.550618114029,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.51820706435848,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.237183532345085,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-08-04T23:37:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.7411627604797,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.375875386655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 214,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 102,
      "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": 154,
      "max_score": null,
      "measured_at": "2026-08-05T01:04:28Z",
      "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": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1283.4924627891278,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.187597579426182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.364069356670375,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "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": 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": 60,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.0576365585443,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.958777248863868,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.08463570631327,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 117,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-08-05T03:19:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 117,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.1028923436827,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.075295219829112,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.2787308949161655,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "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": 117,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.102135627474,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.274718681120902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.823251170389485,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-07-31T02:45:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1264.9730824819735,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.146749768317104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:35:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1274.548733487929,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.85019218818374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.973505697509715,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 59,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:35:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 59,
      "rating_method": "sequential_elo",
      "raw_elo": 1269.0832415302018,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.463532438701474,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.234854341557245,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.5021457048715,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "enabled",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.325282721903957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.829556801099734,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": "2026-08-05T03:20:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1252.718659169334,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.28420303224434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "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": 88,
      "max_score": null,
      "measured_at": "2026-08-05T02:42:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1263.978424801378,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "enabled",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.167965147210907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.747146215609725,
      "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": 2,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-08-05T00:52:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1264.4416980243168,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.91157848915521,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "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": 62,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.6597352187855,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.704436166861854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 95,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1237.0938999004793,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.92797843552678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 224,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "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": 154,
      "max_score": null,
      "measured_at": "2026-08-05T03:19:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 96,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1234.071746624579,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.575835233971056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.335874651846873,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "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": 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": 81,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 97,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1236.8582485470383,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.357692904131554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.864786698060648,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 81,
      "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": 132,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 98,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1160.9615169384278,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.020552189812655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.468842775200363,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 292,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 115,
      "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": 220,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 99,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1130.0626959606705,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "none",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.149445622957767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": 96,
      "max_score": null,
      "measured_at": "2026-08-05T01:51:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 100,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1011.1739414944491,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 5.362618665013622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": "2026-08-05T04:22:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 2105.4058440588437,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:35:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 2000.6669846925447,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 90.99516388242985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:13:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1980.5083189186464,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 89.20483886963211,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 244,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 122,
      "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": "2026-08-05T05:26:27Z",
      "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": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1940.4116114258877,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 85.63226983764412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.8539498938124765,
      "unilateral_faults": 0,
      "wins": 205
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "2026-08-03T14:13:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1871.6449499623504,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 79.53649997231051,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:35:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1841.737030413011,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 76.93117424326455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "2026-08-05T03:42:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1804.4339757540693,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 73.56738030887553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:35:25Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1800.148693292092,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 73.16043333134834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 246,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:59Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1796.997875751851,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 72.91920929796846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.1611854626755758,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:27:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1773.1661991465724,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 70.68089553312336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "2026-08-05T04:28:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.9902710692518,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 69.30390855095736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:43:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1748.3528347421668,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 68.58671985118539,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-03T08:56:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1748.906549027976,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 68.55479086064098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 204,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 71,
      "max_score": null,
      "measured_at": "2026-08-05T04:30:53Z",
      "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": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1725.4022170469711,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 66.11484875005729,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.79454145484633,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 288,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 144,
      "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": 107,
      "max_score": null,
      "measured_at": "2026-07-31T03:29:12Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1720.1848392389459,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 65.68010929815331,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.033231573004961,
      "unilateral_faults": 0,
      "wins": 181
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T02:27:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1714.4239416868895,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 63.864244753090226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.38990374359382,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "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": 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": 48,
      "max_score": null,
      "measured_at": "2026-07-31T03:01:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1691.048118433124,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "highest",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "highest",
        "reasoning_bucket_label": "Intensive",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "reasoning_setting": "highest",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 63.05578896250549,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-08-05T01:31:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1683.4145361717362,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 62.84516887775912,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "2026-08-04T22:40:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1666.4268161629404,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 61.361579256614846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "2026-08-03T14:14:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1648.2632211454757,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 59.67122908962842,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-08-05T00:35:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.7821015362729,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 59.006818274433016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:43:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.5864634999832,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.3941253924312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.8152809272333,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.11004723437738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-08-05T04:28:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1628.4297641341607,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.96187879269228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.3477234865395,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.446840898177854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:30:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.2594219728185,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.248540146399066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 40.79847712741414,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 178,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 89,
      "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": 113,
      "max_score": null,
      "measured_at": "2026-08-05T04:31:02Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.509245658041,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.021020326201075,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.313035635484873,
      "unilateral_faults": 0,
      "wins": 163
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1611.1347947383947,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.45100183671994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 52,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 26,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-08-05T04:30:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.364249622662,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.213321937541714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 40.499923295317174,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-04T22:51:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.2275642237973,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 55.753611595590186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.79936318977655,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "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": 110,
      "max_score": null,
      "measured_at": "2026-08-05T03:42:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.6677941963164,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.873388733034076,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9885453854133264,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 154,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 77,
      "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": "2026-08-05T06:56:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.3503322080414,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.395254355004845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.321327784310522,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "2026-08-05T01:45:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1587.987129981108,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.34437188783892,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 296,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 148,
      "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": 146,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.0224149727546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.257859859863686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.345220975952071,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "2026-08-03T14:14:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.0312688394026,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.14430473568327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 378,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 180,
      "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": 183,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 378,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.489463921882,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.01864952960553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.620576779027561,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "2026-08-03T14:04:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.68608538996,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.58029710675838,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.5214241665924,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.11814186315531,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 232,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "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": 98,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:37Z",
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.7216538502953,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.99731786762054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.566064997422586,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 61,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.7689040110965,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.56860730824784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.878822395858876,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 250,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "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": 134,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:03Z",
      "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": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.3211884250354,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.56133301083614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.4376202060078436,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 252,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "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": 134,
      "max_score": null,
      "measured_at": "2026-08-04T01:46:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.7113363007984,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.5535341301958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.5190135939585359,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.2909691339737,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.65363080364732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-03T15:11:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.7262387953551,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.82745014205055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.831799173767003,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "2026-08-05T04:34:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.4430409822883,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.41140792271331,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 44,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.7598223575376,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.64490710852141,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.017746625155496,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 60,
      "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": "2026-08-05T06:57:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.0991425629509,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.776272775313714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.9176862481661074,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-05T03:28:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.5918102941107,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.58530359916948,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-07-30T20:24:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.9676614194507,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.54371771982972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.52648327229861,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 393,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 196,
      "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": 216,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:27Z",
      "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": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 393,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.5687273778033,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.13494994625827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.12514876054421956,
      "unilateral_faults": 0,
      "wins": 177
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:34:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.9713046631996,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.776416361264104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.080592941617738,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T01:37:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.9851381905353,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.33771077624585,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:31:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.7500742829843,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.42172085598957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.621021663051927,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.2719353363145,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.359421410539206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.724920543044455,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.1898440671557,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.15956696391413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 113,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.2957378785,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "enabled",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.52220457729294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.288270414847073,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 65,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-08-05T04:31:02Z",
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 65,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.2585103323468,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.412038961161755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.542286733757642,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-08-05T04:30:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.0279851395217,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.204352917679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.177254191272162,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-08-03T12:28:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.7320098290559,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.598572223588526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 60,
      "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": 100,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.8991729354007,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.53688282449636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.160696943995934,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-03T15:18:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.0315415173136,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.3549780388027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.386417506374595,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 252,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "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": "2026-08-05T05:24:25Z",
      "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": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.751951341211,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.11567729374995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.8522727272727293,
      "unilateral_faults": 0,
      "wins": 128
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.775336915899,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.97118928762754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T05:19:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.7290822266407,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "enabled",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.83692106824891,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.54985278838047,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-08-03T12:43:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.0972054047072,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.26086585514032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 260,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 8,
      "distinct_rated_opponents": 130,
      "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": 230,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.3414112535602,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.07624386646105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.27158650165324,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.5051547512048,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.61113499633033,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "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": 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": "2026-08-05T00:37:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.4833878281063,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.79378137592323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "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": 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": "2026-08-04T21:46:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.3500810499045,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.25943897025135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.85345304153558,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 190,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "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": 115,
      "max_score": null,
      "measured_at": "2026-07-31T03:07:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.8724654180028,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.16873173236723,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.283112930469331,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-08-05T02:09:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.3878157010372,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.95277949062936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 42
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 113,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:47Z",
      "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": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.6505860863158,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.44754596890132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.906255061212047,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T06:57:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.2617719734535,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.895583637620526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.438955443770794,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 96,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.6835123650214,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.721339092090396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.16857499447537,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-08-05T04:09:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.4735570462385,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.34465187857206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-08-05T01:17:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.2791878007524,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.45926297584206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.926543555546573,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-08-04T23:37:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.612305369056,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.13192466394973,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.45013723807159,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.2913737732042,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.285058901033004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 326,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 161,
      "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": 188,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:25Z",
      "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": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.7381559646585,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.17318662888423,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.000874675844361,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 220,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 125,
      "max_score": null,
      "measured_at": "2026-08-03T22:56:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.401767487915,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.05907819296716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.936433935731518,
      "unilateral_faults": 2,
      "wins": 93
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 52,
      "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": 113,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.7115581527555,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.215324657126956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.94927125227558,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 73,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:50:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 73,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.6689853530577,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.214369480459318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.80894910339042,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1315.0784435685223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.228737245304664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.76799953545848,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-08-05T04:12:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.9786118237457,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.74104627006085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.007326216468247,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 225,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 112,
      "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": 138,
      "max_score": null,
      "measured_at": "2026-08-03T22:28:24Z",
      "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": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1287.3461805364666,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.498910992576068,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.3747745509860616,
      "unilateral_faults": 1,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "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": 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": "2026-08-05T01:38:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.427688695992,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.47064359767043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.12451556018153,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 457,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 228,
      "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": 318,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 457,
      "rating_method": "sequential_elo",
      "raw_elo": 1285.053507576868,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.32895163665409,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.9010645474206243,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 236,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 156,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:56Z",
      "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": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.7241426466258,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "none",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.618036428605613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4952944368626584,
      "unilateral_faults": 4,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": "2026-08-03T21:49:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1273.2695604121793,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.19428053874851,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 2,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1262.0756595302967,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.230925188782717,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T05:19:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1253.5544921999174,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.992806942856724,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-08-05T04:31:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1256.5767702858623,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.83779534181248,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.51693271964983,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 98,
      "max_score": null,
      "measured_at": "2026-08-05T04:22:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1210.0225762192022,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.461087260708307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.850427786204904,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T05:26:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1190.757908767719,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.369589094882354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 327,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 157,
      "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": 244,
      "max_score": null,
      "measured_at": "2026-08-04T01:46:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 95,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 322,
      "rating_method": "sequential_elo",
      "raw_elo": 1167.1939517552057,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.762689788970278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.29384956406377,
      "unilateral_faults": 5,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 107,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-08-03T23:25:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 96,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1140.8549909594703,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 14.402666706405672,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 1,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-08-04T23:43:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 97,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1136.958953317386,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 14.05665305055863,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-07-31T03:28:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 98,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1123.552445089051,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 12.693314222369741,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": "2026-08-04T01:12:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 99,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1097.921478157074,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 10.523618948427423,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 2,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "2026-08-05T01:39:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 100,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1030.1908334918917,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 4.666816393696632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 101,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 980.6285194650904,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-05T04:44:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 2055.9331893482595,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 348,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 174,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-05T02:34:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 348,
      "rating_method": "sequential_elo",
      "raw_elo": 1959.177771791579,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 88.85644622319035,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4885350752759137,
      "unilateral_faults": 0,
      "wins": 304
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 262,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 131,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1897.8126562352456,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 82.16198499155695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 216
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1854.8373059774533,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 76.98336681634814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 222,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-05T04:52:03Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1829.26608314685,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 74.0721732581313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.4969716034024056,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.1758610356108,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 70.00316477029536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-08-03T08:03:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1785.981513065026,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 69.11838234678588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-08-03T04:47:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1782.5639360440102,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 68.98590691472927,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 222,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 111,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-08-05T03:58:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1796.9439417067679,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 68.96755045489611,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.51136721509174,
      "unilateral_faults": 0,
      "wins": 291
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T04:44:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1774.4726146237526,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 68.19729379593623,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 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": 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": 37,
      "max_score": null,
      "measured_at": "2026-07-31T03:36:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1770.67508474561,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "highest",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "highest",
        "reasoning_bucket_label": "Intensive",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "reasoning_setting": "highest",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 67.17363802127772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": 30,
      "max_score": null,
      "measured_at": "2026-08-03T01:17:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1746.3197512997453,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 64.91944958274557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 232,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 8,
      "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": 62,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1748.4616627962346,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 64.90150228152228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.241307227332022,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 70,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1726.5150017837482,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 62.96894118841835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 138,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 69,
      "draws": 3,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-04T23:19:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1742.9337561743264,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 61.644694598987854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.93195887871912,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "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": 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": 63,
      "max_score": null,
      "measured_at": "2026-08-04T21:52:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1701.9630242155704,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 59.511553845816714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.2943419813913195,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T01:31:37Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1667.5092199905735,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.35480356946494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.22027992219475,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 138,
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 69,
      "draws": 35,
      "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": "2026-08-05T04:53:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1671.3613009319051,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.79745130191461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.195323654719896,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 11,
      "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": "2026-08-05T05:18:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1651.8394288276704,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.05623433107263,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 22,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T04:23:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.3119824922603,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.93948176668485,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1606.092096601223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.12291169798428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 302,
      "capped_draws": 90,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 151,
      "draws": 90,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-07-31T20:23:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.288920722461,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.07415527631838,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.859591937440758,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 31,
      "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": "2026-08-05T04:44:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.607560959858,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.98316602186302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-02T22:46:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.6942987321636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.91606278892348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 386,
      "capped_draws": 169,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 187,
      "draws": 169,
      "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": 91,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 386,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.4716211595342,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.330135882794195,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.2967902623622957,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 52,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-03T13:54:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.1308178470354,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.48130098619828,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 106,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "draws": 106,
      "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": "2026-08-03T03:56:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.3284416661595,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.39648748043947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 17,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-08-02T23:32:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.5659164262063,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.56442313471822,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-08-02T23:32:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.6098803293485,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.69816826394159,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 264,
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 127,
      "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": 93,
      "max_score": null,
      "measured_at": "2026-08-05T04:52:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.9101728693004,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.43308067787763,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.3089127354028465,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 380,
      "capped_draws": 170,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 190,
      "draws": 170,
      "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": 114,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.9622489746218,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.20581487904527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.3313144022682706,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 376,
      "capped_draws": 137,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 183,
      "draws": 137,
      "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": 142,
      "max_score": null,
      "measured_at": "2026-08-05T04:51:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 376,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.8881549864773,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.71113006655985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.7682804277891364,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 142,
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 71,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.638154159525,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.01219161214689,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.40895509928201,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T03:28:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.332639053323,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.25142205084722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 42,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-04T21:46:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.1240261408266,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.78471494023906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.83255510180566,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "capped_draws": 70,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 65,
      "draws": 110,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:47Z",
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.5107778326746,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.57155276802534,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.974048701260934,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 222,
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 111,
      "draws": 104,
      "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": 95,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.2886959682157,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.48570871237849,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 40.64520801091697,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 520,
      "capped_draws": 331,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 255,
      "draws": 331,
      "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": 105,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 520,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.8757642909575,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.38644028078468,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.42613636363636465,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-03T12:36:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.7534965706259,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.039349146950016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-03T06:08:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.4436413007966,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.985519854727933,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 71,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T04:23:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.7661257245363,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.014574794367363,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "capped_draws": 101,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 101,
      "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": "2026-08-05T01:22:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.5223595698037,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.760804539439587,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 109,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T03:32:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.7781869391822,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.734330041940417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 156,
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.8590805710878,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.65874799969496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 95,
      "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": "2026-08-05T04:43:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.1134240521621,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.601263953234557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "capped_draws": 105,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 70,
      "draws": 105,
      "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": "2026-08-05T03:33:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.5477969238084,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.53729144867848,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 99,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 99,
      "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": "2026-08-05T05:41:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.4172481872668,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.495214909397852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 278,
      "capped_draws": 244,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 133,
      "draws": 244,
      "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": "2026-08-05T05:41:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.369819758583,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.390406342527847,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 99,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 99,
      "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": "2026-08-05T03:33:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.861164888524,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.31922167829491,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "capped_draws": 91,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 91,
      "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": "2026-08-05T05:41:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.374254888266,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.291653340113125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 91,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 91,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-04T07:10:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.3097970155627,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.273880023544745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 2,
      "wins": 6
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 304,
      "capped_draws": 249,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 152,
      "draws": 249,
      "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": "2026-07-31T03:35:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 303,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.623772094612,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.101805618887024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.765621052642042,
      "unilateral_faults": 1,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 104,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "draws": 104,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.1245896868447,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.09490742966929,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "draws": 31,
      "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": "2026-08-03T12:45:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.8212261015778,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.081470669645384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.237183532345085,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 400,
      "capped_draws": 290,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 197,
      "draws": 290,
      "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": 83,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:30Z",
      "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": 398,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.178803898413,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.926757621782304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.8250054507008079,
      "unilateral_faults": 2,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "capped_draws": 116,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 116,
      "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": "2026-08-05T03:33:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.5203475276332,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "none",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.82104904701147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "capped_draws": 114,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 114,
      "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": "2026-08-04T22:07:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.331625152364,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.747877916943,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 408,
      "capped_draws": 239,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 204,
      "draws": 239,
      "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": 108,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 408,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.6318876144662,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.47285784764608,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 96,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 96,
      "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": "2026-07-31T02:32:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.8696093056199,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.4031104365134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 378,
      "capped_draws": 329,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 148,
      "draws": 329,
      "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": "2026-08-05T05:41:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 374,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.8180210731284,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "none",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.381746596189068,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "capped_draws": 105,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 105,
      "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": "2026-08-05T05:41:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.2782648293512,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.37599577178315,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "capped_draws": 112,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.3766557322458,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.19008980579632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 278,
      "capped_draws": 240,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 133,
      "draws": 240,
      "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": "2026-08-05T05:40:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 277,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.6618782515638,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.059297656013577,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "capped_draws": 102,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 102,
      "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": "2026-08-04T23:29:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.747777600697,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.892763334314395,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "capped_draws": 90,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 50,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:49Z",
      "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": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.4319843854755,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.88284327640182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.748044770341348,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 42,
      "draws": 92,
      "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": "2026-08-05T01:39:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.2111834594807,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.797657036523127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.913534972537988,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 92,
      "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": "2026-08-05T05:33:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.1694751108657,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.74278235761671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 44,
      "draws": 116,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T00:36:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.2115047229668,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.57813859269058,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.090087987331263,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 106,
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 53,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.3374186238389,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": 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"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.53818816474888,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.689018606881785,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 402,
      "capped_draws": 311,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 198,
      "draws": 311,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 402,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.5660382499407,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.52517243388469,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.44449391112387104,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 92,
      "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": "2026-08-05T01:39:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.8948685173345,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.513431403839135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.883146202654,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.325075245894105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.976534673506283,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 41,
      "draws": 106,
      "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": "2026-08-05T05:18:47Z",
      "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": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.249176342982,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.15585015743753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.804373924048683,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "capped_draws": 79,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 52,
      "draws": 151,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0487153291788,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/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"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.103391256384768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 92,
      "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": "2026-07-31T02:43:26Z",
      "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": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.890887252805,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.961738933840852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 81,
      "capped_draws": 61,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 61,
      "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": "2026-08-05T05:25:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 81,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.0575438734552,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.825513643960814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.465763037423269,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "capped_draws": 181,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 181,
      "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": "2026-07-31T03:35:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.0566857622682,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.706437896899708,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.280733777820661,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 41,
      "draws": 105,
      "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": "2026-08-05T03:27:52Z",
      "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": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.3196679470848,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.653180799629084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.698067098122827,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 86,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T04:23:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.1496435571894,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.37839192404362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "capped_draws": 128,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 81,
      "draws": 128,
      "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": "2026-08-05T05:26:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.7950522422157,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.11024043322827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.542957485854352,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 129,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 129,
      "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": "2026-08-05T05:41:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.731723298986,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.798477633166108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.9115222168389,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.78316364121671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.55344771392958,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 70,
      "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": "2026-08-05T05:41:08Z",
      "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": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.438879424766,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.48313253075837,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.77863397214846,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 36,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "draws": 85,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-04T23:45:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.229001478985,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.61720886725491,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.836607386351783,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T05:41:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.6511322068186,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.170311606444997,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.55344771392958,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T00:38:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.141283069378,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.049881684857795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.747146215609725,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "capped_draws": 110,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 70,
      "draws": 110,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T04:49:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.202537480436,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.730135675874582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 152,
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 76,
      "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": 71,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.232126813642,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.15352632879835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.767357465638472,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:53:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1381.5144800797461,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.756531763359927,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.007943739905976,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 36,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "draws": 85,
      "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": "2026-08-05T02:15:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.8979860686834,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.497204299638256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.85345304153558,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 98,
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 49,
      "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": 77,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.6641089407344,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.450319954890443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.82927958473947,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 238,
      "capped_draws": 169,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 119,
      "draws": 169,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.3990143028504,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.075114883794193,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.8947351529780132,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 37,
      "draws": 62,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T04:44:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.4925532767802,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "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"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.92911913796267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.375226195907118,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 69,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.8995387907771,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.440337873964644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-08-05T04:22:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 95,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.5846777749914,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.935559087203618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 39,
      "draws": 98,
      "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": "2026-08-05T04:28:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 96,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1361.4513228516012,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "enabled",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.660787526239893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.091483237436318,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "draws": 89,
      "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": "2026-08-04T08:41:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 97,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.055533810906,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.35129652009281,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.517288899732886,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "draws": 62,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T04:51:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 98,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.6468603917838,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.58079185799611,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.772182566181264,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-03T02:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 99,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.54682570675,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.608657739305404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-07-31T03:36:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 100,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1305.168682733359,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 13.117033955210568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.06074898572802,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "draws": 74,
      "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": "2026-08-05T03:58:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 101,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.4253612380444,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 12.88406623711618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.20639198938312,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "draws": 16,
      "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": 89,
      "max_score": null,
      "measured_at": "2026-08-05T02:33:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 102,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1221.5615690949933,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 3.5186261065286026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.63492938218381,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 41,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 41,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 48
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 7,
        "max": 2.09943,
        "mean": 0.703821875,
        "median": 0.48028875,
        "min": 0.2178175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 48
        },
        "run_count": 48,
        "token_priced_attempt_count": 48,
        "total": 33.78345
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 41,
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 41,
      "first_pass_rate": 0.8541666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:35:16Z",
      "losses": null,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 39.830660376507744,
      "model_code_failure_rate": 0.14583333333333334,
      "model_code_failures": 7,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1806.9912053246612,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 72.35173547471699,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 1.0782631249999999,
        "median": 0.5065824999999999,
        "min": 0.06826499999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 28
        },
        "run_count": 24,
        "token_priced_attempt_count": 28,
        "total": 25.878314999999997
      },
      "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": "2026-08-05T06:55:12Z",
      "losses": null,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 17.553436099642553,
      "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": 1667.3543324590628,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 4,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 56.37407351184413,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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-2026-07-30": 27
        },
        "run_count": 26,
        "token_priced_attempt_count": 27,
        "total": 85.663355
      },
      "codegen_evaluated_cells": 26,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "2026-08-05T05:17:02Z",
      "losses": null,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 19.935559087203618,
      "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": 1636.8357717450515,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.038461538461538464,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 55.07733741392539,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 0.20305499999999999,
        "min": 0.131495,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 25
        },
        "run_count": 24,
        "token_priced_attempt_count": 25,
        "total": 10.456240000000001
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "2026-08-05T04:43:45Z",
      "losses": null,
      "max_score": 86.15355149666183,
      "measured_at": null,
      "min_score": 16.591663020618228,
      "model_code_failure_rate": 0.08333333333333333,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1606.4142181382563,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 50.379878430994545,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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-2026-07-30": 26
        },
        "run_count": 24,
        "token_priced_attempt_count": 26,
        "total": 26.566349999999996
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "2026-08-05T05:26:46Z",
      "losses": null,
      "max_score": 90.99516388242985,
      "measured_at": null,
      "min_score": 12.006801731616441,
      "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": 1618.9255599123398,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 49.68055448034795,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 58,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 58,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 132
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.19006573333333335,
        "mean": 0.10711824444444444,
        "median": 0.09929546666666667,
        "min": 0.041110400000000005,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 132
        },
        "recorded_attempt_count": 132,
        "run_count": 64,
        "total": 7.089512
      },
      "codegen_evaluated_cells": 64,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 88,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 52,
      "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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 16,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:54:57Z",
      "losses": null,
      "max_score": 88.85644622319035,
      "measured_at": null,
      "min_score": 16.238936021776848,
      "model_code_failure_rate": 0.09375,
      "model_code_failures": 6,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.7464870120425,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 6,
      "repaired_rate": 0.09375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 48.54006988577404,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 12.137519999999999,
        "mean": 2.8005991666666663,
        "median": 0.15809499999999999,
        "min": 0.0542775,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 32
        },
        "run_count": 25,
        "token_priced_attempt_count": 32,
        "total": 67.27386999999999
      },
      "codegen_evaluated_cells": 25,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "2026-08-05T06:54:57Z",
      "losses": null,
      "max_score": 74.75879788264669,
      "measured_at": null,
      "min_score": 25.620832892368888,
      "model_code_failure_rate": 0.04,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.083731260625,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 7,
      "repaired_rate": 0.28,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 44.77072465337242,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 42,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 42,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 126
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.531673125,
        "mean": 0.264606278125,
        "median": 0.24728879999999998,
        "min": 0.0411735,
        "recorded_attempt_count": 126,
        "run_count": 48,
        "total": 12.701101349999998
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 70,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 34,
      "first_pass_rate": 0.7083333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:55:12Z",
      "losses": null,
      "max_score": 83.67694797963125,
      "measured_at": null,
      "min_score": 15.356957668247802,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 6,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.8888833981741,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 43.06068399835349,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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_list_price_estimate": 24
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.73533,
        "mean": 0.29615479166666664,
        "median": 0.19681749999999998,
        "min": 0.09594,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 16,
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 24,
        "token_priced_attempt_count": 24,
        "total": 7.107714999999999
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 40,
      "failed_game_aliases": [],
      "first_pass_admitted": 24,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:15Z",
      "losses": null,
      "max_score": 64.91944958274557,
      "measured_at": null,
      "min_score": 17.12149396001877,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.5767722201258,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 42.42327640773364,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 52,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 52,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 114
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 1.1177706,
        "mean": 0.4278839708333333,
        "median": 0.32150055,
        "min": 0.0587988,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 114
        },
        "recorded_attempt_count": 114,
        "run_count": 58,
        "total": 29.4665766
      },
      "codegen_evaluated_cells": 57,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 89,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 46,
      "first_pass_rate": 0.8070175438596491,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_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": "2026-08-05T06:55:02Z",
      "losses": null,
      "max_score": 76.9153537911332,
      "measured_at": null,
      "min_score": 17.703162245681458,
      "model_code_failure_rate": 0.08771929824561403,
      "model_code_failures": 5,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.531635716907,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 6,
      "repaired_rate": 0.10526315789473684,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 42.26124520320811,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 24,
        "cost_basis_counts": {
          "estimated": 1,
          "local_list_price_estimate": 28,
          "provider_dashboard_reconciled": 1
        },
        "evidence_basis": "Mixed: Provider-reported + Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.4567,
        "mean": 0.17373851388888892,
        "median": 0.0769495,
        "min": 0.049788,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-07-30": 27
        },
        "recorded_attempt_count": 2,
        "run_count": 27,
        "token_priced_attempt_count": 28,
        "total": 5.0887600000000015
      },
      "codegen_evaluated_cells": 27,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 26,
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 25,
      "first_pass_rate": 0.9259259259259259,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_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": "2026-08-05T05:41:08Z",
      "losses": null,
      "max_score": 62.31323923781224,
      "measured_at": null,
      "min_score": 22.62500365197257,
      "model_code_failure_rate": 0.037037037037037035,
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.2299202305887,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.037037037037037035,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 41.06043574753804,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": {
          "estimated": 2,
          "local_standard_estimate": 73
        },
        "evidence_basis": "Mixed: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 1.5164726249999998,
        "mean": 0.44590651875000004,
        "median": 0.24021375,
        "min": 0.01259225,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-07-30": 73
        },
        "recorded_attempt_count": 2,
        "run_count": 62,
        "token_priced_attempt_count": 73,
        "total": 21.432919649999995
      },
      "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": "2026-08-05T06:55:18Z",
      "losses": null,
      "max_score": 72.91920929796846,
      "measured_at": null,
      "min_score": 16.762689788970278,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.355028803255,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.13333333333333333,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.03721344850252,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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-2026-07-30": 28
        },
        "run_count": 26,
        "token_priced_attempt_count": 28,
        "total": 29.297331
      },
      "codegen_evaluated_cells": 26,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "2026-08-05T05:41:40Z",
      "losses": null,
      "max_score": 79.30739463261588,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.7079033493483,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 2,
      "repaired_rate": 0.07692307692307693,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 37.49502654987403,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": {
          "estimated": 2,
          "local_standard_estimate": 134
        },
        "evidence_basis": "Mixed: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 16,
        "max": 0.38568888333333334,
        "mean": 0.10722314947916667,
        "median": 0.02520601875,
        "min": 0.0058062875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-07-30": 134
        },
        "recorded_attempt_count": 2,
        "run_count": 84,
        "token_priced_attempt_count": 134,
        "total": 6.988288499999999
      },
      "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": "2026-08-05T06:55:07Z",
      "losses": null,
      "max_score": 88.3001049099167,
      "measured_at": null,
      "min_score": 15.510539068363032,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.1075271026925,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 32,
      "repaired_rate": 0.3950617283950617,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 33.3949723013493,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 43,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 43,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 132
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.0719635,
        "mean": 0.03858281041666666,
        "median": 0.037386975,
        "min": 0.012759,
        "recorded_attempt_count": 132,
        "run_count": 48,
        "total": 1.8519749
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 70,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-07"
      ],
      "first_pass_admitted": 36,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:55:18Z",
      "losses": null,
      "max_score": 58.42525560215735,
      "measured_at": null,
      "min_score": 16.907630545609305,
      "model_code_failure_rate": 0.10416666666666667,
      "model_code_failures": 5,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.733958274643,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 7,
      "repaired_rate": 0.14583333333333334,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 30.70449655724711,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 24,
        "cost_basis_counts": {
          "provider_reported": 48
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.01660212,
        "mean": 0.00430918425,
        "median": 0.0025298300000000003,
        "min": 0.00045831,
        "recorded_attempt_count": 48,
        "run_count": 24,
        "total": 0.10342042200000003
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 31,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-05",
        "GB2-07"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:31Z",
      "losses": null,
      "max_score": 64.6891432709365,
      "measured_at": null,
      "min_score": 9.425383107713568,
      "model_code_failure_rate": 0.20833333333333334,
      "model_code_failures": 5,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.3075210731013,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 13,
      "repaired_rate": 0.5416666666666666,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 27.466345546443296,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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-2026-07-30": 19
        },
        "run_count": 16,
        "token_priced_attempt_count": 19,
        "total": 16.69817
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "2026-08-05T04:44:21Z",
      "losses": null,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 48.695876476828644,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 74.37835430818026,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 0.41891503124999996,
        "median": 0.4031475,
        "min": 0.254883,
        "recorded_attempt_count": 37,
        "run_count": 16,
        "total": 6.7026405
      },
      "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": "2026-08-05T06:54:47Z",
      "losses": null,
      "max_score": 88.04000833669701,
      "measured_at": null,
      "min_score": 12.88406623711618,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 14,
      "repaired_rate": 0.875,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 45.36004182416376,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 8,
        "cost_basis_counts": {
          "exact_cumulative_delta": 1,
          "provider_reported": 64
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.25823185295,
        "mean": 0.20846239076375003,
        "median": 0.20662718916666667,
        "min": 0.13654539825,
        "recorded_attempt_count": 65,
        "run_count": 29,
        "total": 5.97530434986
      },
      "codegen_evaluated_cells": 27,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 64,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.1111111111111111,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_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": "2026-08-05T05:05:01Z",
      "losses": null,
      "max_score": 78.66120174874919,
      "measured_at": null,
      "min_score": 16.341761309376864,
      "model_code_failure_rate": 0.25925925925925924,
      "model_code_failures": 7,
      "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": 1525.9885572714265,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 17,
      "repaired_rate": 0.6296296296296297,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 40.153146573452666,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 1,
        "cost_basis_counts": {
          "estimated": 1,
          "local_standard_estimate": 1
        },
        "evidence_basis": "Mixed: Recorded attempt + Standard list-price estimate",
        "max": 0.0023425,
        "mean": 0.0023425,
        "median": 0.0023425,
        "min": 0.0023425,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 1,
          "boardgame-list-prices-2026-07-30": 1
        },
        "recorded_attempt_count": 1,
        "run_count": 1,
        "token_priced_attempt_count": 1,
        "total": 0.0023425
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 1,
      "failed_game_aliases": [],
      "first_pass_admitted": 1,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:02:05Z",
      "losses": null,
      "max_score": 39.478292990152276,
      "measured_at": null,
      "min_score": 39.478292990152276,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 39.478292990152276,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 0.7872815620000001
      },
      "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": "2026-08-05T05:11:41Z",
      "losses": null,
      "max_score": 76.14344213568862,
      "measured_at": null,
      "min_score": 17.2055412078098,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 3,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 39.234072665806686,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": "2026-08-05T05:17:07Z",
      "losses": null,
      "max_score": 66.15885507474644,
      "measured_at": null,
      "min_score": 19.35129652009281,
      "model_code_failure_rate": 0.2,
      "model_code_failures": 3,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.5333333333333333,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.62200379032396,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 0.45464499999999997,
        "mean": 0.22978835937499997,
        "median": 0.1997375,
        "min": 0.1418975,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 19
        },
        "run_count": 16,
        "token_priced_attempt_count": 19,
        "total": 3.6766137500000005
      },
      "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": "2026-08-05T05:19:06Z",
      "losses": null,
      "max_score": 66.50580979104048,
      "measured_at": null,
      "min_score": 16.793318043756123,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.44567822854766,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 0.12185499999999999,
        "mean": 0.05695140625,
        "median": 0.036751875,
        "min": 0.015285,
        "recorded_attempt_count": 24,
        "run_count": 16,
        "total": 0.9112224999999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "2026-08-05T05:35:11Z",
      "losses": null,
      "max_score": 68.55479086064098,
      "measured_at": null,
      "min_score": 20.42853187574935,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 37.52968553445464,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 1.283003154
      },
      "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": "2026-08-05T05:26:41Z",
      "losses": null,
      "max_score": 54.35480356946494,
      "measured_at": null,
      "min_score": 20.78553102586511,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 37.04647459414284,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.09459400000000001,
        "mean": 0.0571955,
        "median": 0.043012,
        "min": 0.032534,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 0.457564
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "2026-08-05T05:41:31Z",
      "losses": null,
      "max_score": 56.63398289929676,
      "measured_at": null,
      "min_score": 14.75877111394388,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 36.39316993293499,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 29,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 29,
        "cell_count": 24,
        "cost_basis_counts": {
          "estimated": 40,
          "local_standard_estimate": 29
        },
        "evidence_basis": "Mixed: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 19,
        "max": 0.17217,
        "mean": 0.08358424999999998,
        "median": 0.08653749999999999,
        "min": 0.037309999999999996,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 13,
          "boardgame-list-prices-2026-07-30": 56
        },
        "recorded_attempt_count": 40,
        "run_count": 48,
        "token_priced_attempt_count": 29,
        "total": 4.201686
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 52,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-08"
      ],
      "first_pass_admitted": 29,
      "first_pass_rate": 0.6041666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:08Z",
      "losses": null,
      "max_score": 57.446840898177854,
      "measured_at": null,
      "min_score": 24.48313253075837,
      "model_code_failure_rate": 0.3958333333333333,
      "model_code_failures": 19,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.1686500715255,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 34.32604377644525,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": "2026-08-05T05:34:43Z",
      "losses": null,
      "max_score": 53.061970706152835,
      "measured_at": null,
      "min_score": 19.32369832555091,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 32.35197445455003,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 0.51646592
      },
      "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": "2026-08-05T03:48:47Z",
      "losses": null,
      "max_score": 69.54336053342072,
      "measured_at": null,
      "min_score": 10.523618948427423,
      "model_code_failure_rate": 0.29411764705882354,
      "model_code_failures": 5,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 7,
      "repaired_rate": 0.4117647058823529,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 32.07800689820225,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 68
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.0068074,
        "mean": 0.0032179299999999995,
        "median": 0.00314426,
        "min": 0.0012446800000000002,
        "recorded_attempt_count": 68,
        "run_count": 28,
        "total": 0.09094181999999999
      },
      "codegen_evaluated_cells": 28,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 34,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 4,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:54:33Z",
      "losses": null,
      "max_score": 52.809153048377176,
      "measured_at": null,
      "min_score": 15.67108825376102,
      "model_code_failure_rate": 0.17857142857142858,
      "model_code_failures": 5,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.32142857142857145,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 30.81606916124975,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 25
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.007539277999999999,
        "mean": 0.0022565913437500003,
        "median": 0.0014932259999999998,
        "min": 0.00090937,
        "recorded_attempt_count": 25,
        "run_count": 17,
        "total": 0.041725613
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "2026-08-05T05:11:51Z",
      "losses": null,
      "max_score": 72.251918530255,
      "measured_at": null,
      "min_score": 6.649465460691646,
      "model_code_failure_rate": 0.23529411764705882,
      "model_code_failures": 4,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 4,
      "repaired_rate": 0.23529411764705882,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 30.676169136799764,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 63
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.017371818,
        "mean": 0.006060049642083332,
        "median": 0.0031725295999999997,
        "min": 0.0018257240000000001,
        "recorded_attempt_count": 63,
        "run_count": 40,
        "total": 0.21170622898000002
      },
      "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": 0.48717948717948717,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_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": "2026-08-05T05:41:49Z",
      "losses": null,
      "max_score": 54.873388733034076,
      "measured_at": null,
      "min_score": 18.666770219098307,
      "model_code_failure_rate": 0.23076923076923078,
      "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": 1401.0226212988762,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 11,
      "repaired_rate": 0.28205128205128205,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 30.569590367410274,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 32
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.038769960000000006,
        "mean": 0.0137899931625,
        "median": 0.009162978799999999,
        "min": 0.0014804776,
        "recorded_attempt_count": 32,
        "run_count": 17,
        "total": 0.2447998044
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 36,
      "failed_game_aliases": [
        "GB2-02",
        "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": "2026-08-05T05:41:45Z",
      "losses": null,
      "max_score": 55.431385487557364,
      "measured_at": null,
      "min_score": 18.203309021107163,
      "model_code_failure_rate": 0.23529411764705882,
      "model_code_failures": 4,
      "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": 1435.876838774738,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.47058823529411764,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 30.2604654370234,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": "2026-08-05T03:57:18Z",
      "losses": null,
      "max_score": 49.01545827784715,
      "measured_at": null,
      "min_score": 19.625108861534393,
      "model_code_failure_rate": 0.2857142857142857,
      "model_code_failures": 4,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 5,
      "repaired_rate": 0.35714285714285715,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 30.224370973946137,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 0.78755832
      },
      "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": "2026-08-05T05:18:47Z",
      "losses": null,
      "max_score": 49.2908922032663,
      "measured_at": null,
      "min_score": 5.922992138645202,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 3,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.5625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 29.366981281242193,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 108
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.103943664,
        "mean": 0.050012701874999996,
        "median": 0.041983026,
        "min": 0.006392298,
        "recorded_attempt_count": 108,
        "run_count": 32,
        "total": 1.6004064599999999
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 38,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 17,
      "first_pass_rate": 0.53125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:54:28Z",
      "losses": null,
      "max_score": 48.45429450824968,
      "measured_at": null,
      "min_score": 11.347553349665287,
      "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_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.28125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 28.925069936877264,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 24,
        "cost_basis_counts": {
          "provider_reported": 59
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.11219570000000001,
        "mean": 0.0416694575,
        "median": 0.033877925,
        "min": 0.00984735,
        "recorded_attempt_count": 59,
        "run_count": 24,
        "total": 1.00006698
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 22,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:59Z",
      "losses": null,
      "max_score": 53.50967288140359,
      "measured_at": null,
      "min_score": 13.030258973366303,
      "model_code_failure_rate": 0.4583333333333333,
      "model_code_failures": 11,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.5511652416264,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 10,
      "repaired_rate": 0.4166666666666667,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 28.615857137245154,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 56
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.065385,
        "mean": 0.0335284171875,
        "median": 0.033685425,
        "min": 0.01864685,
        "recorded_attempt_count": 56,
        "run_count": 25,
        "total": 0.82244845
      },
      "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": "2026-08-05T04:29:54Z",
      "losses": null,
      "max_score": 61.2479202482627,
      "measured_at": null,
      "min_score": 12.693314222369741,
      "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": 1440.634126901103,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 12,
      "repaired_rate": 0.48,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 28.422476382747316,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 27,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 27,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 145
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 21,
        "max": 0.302804525,
        "mean": 0.12502029041666668,
        "median": 0.082332765,
        "min": 0.01945095,
        "recorded_attempt_count": 145,
        "run_count": 48,
        "total": 6.000973940000001
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 36,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 16,
      "first_pass_rate": 0.3333333333333333,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:54Z",
      "losses": null,
      "max_score": 62.96894118841835,
      "measured_at": null,
      "min_score": 14.327060935420919,
      "model_code_failure_rate": 0.4375,
      "model_code_failures": 21,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.7680865844716,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 11,
      "repaired_rate": 0.22916666666666666,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 26.762421399241273,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 12,
        "max": 0.215758025,
        "mean": 0.132049078125,
        "median": 0.1281735,
        "min": 0.061553000000000004,
        "recorded_attempt_count": 53,
        "run_count": 24,
        "total": 3.40579925
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "2026-08-05T05:35:20Z",
      "losses": null,
      "max_score": 59.67122908962842,
      "measured_at": null,
      "min_score": 3.5186261065286026,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 12,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 12,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 23.69500431162519,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 45
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 13,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 45,
        "run_count": 24,
        "total": 0.0
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "2026-08-05T05:19:01Z",
      "losses": null,
      "max_score": 45.91779335384322,
      "measured_at": null,
      "min_score": 19.154491325362542,
      "model_code_failure_rate": 0.5416666666666666,
      "model_code_failures": 13,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333334,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 23.36926343486995,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 37
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.0422995,
        "mean": 0.018814015625,
        "median": 0.017673,
        "min": 0.00402875,
        "recorded_attempt_count": 37,
        "run_count": 16,
        "total": 0.30102425
      },
      "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": "2026-08-05T05:18:42Z",
      "losses": null,
      "max_score": 41.949273557550775,
      "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": 1223.9420873648835,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.5625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 21.88903546237954,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 16,
        "cost_basis_counts": {
          "provider_reported": 92
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 15,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 92,
        "run_count": 32,
        "total": 0.0
      },
      "codegen_evaluated_cells": 31,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 22,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.22580645161290322,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:59Z",
      "losses": null,
      "max_score": 43.52220457729294,
      "measured_at": null,
      "min_score": 11.744571555937974,
      "model_code_failure_rate": 0.4838709677419355,
      "model_code_failures": 15,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.2903225806451613,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 21.588380852524416,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 28
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.3927285,
        "mean": 0.116635875,
        "median": 0.0747585,
        "min": 0.0223935,
        "recorded_attempt_count": 28,
        "run_count": 17,
        "total": 2.2589025
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 12,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.23529411764705882,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:02:41Z",
      "losses": null,
      "max_score": 37.07858798158563,
      "measured_at": null,
      "min_score": 15.89051825604416,
      "model_code_failure_rate": 0.5294117647058824,
      "model_code_failures": 9,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 4,
      "repaired_rate": 0.23529411764705882,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 21.46238785938686,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 1646,
      "capped_draws": 24,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.551725,
        "mean": 0.44617968750000003,
        "median": 0.45788,
        "min": 0.33828,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 7.1388750000000005
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 74.34745635799887,
      "contributing_entrants": null,
      "distinct_rated_opponents": 823,
      "draws": 216,
      "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": "2026-08-05T05:35:16Z",
      "losses": 291,
      "max_score": 97.66928476084789,
      "measured_at": null,
      "min_score": 39.830660376507744,
      "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": 1646,
      "rating_method": "sequential_elo",
      "raw_elo": 1810.738566838014,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 71.90649629376915,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1139
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 758,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.6981,
        "mean": 0.5046499999999999,
        "median": 0.511355,
        "min": 0.33027,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.0371999999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 67.61938022412934,
      "contributing_entrants": null,
      "distinct_rated_opponents": 377,
      "draws": 88,
      "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": "2026-08-05T04:34:24Z",
      "losses": 178,
      "max_score": 80.83296452654382,
      "measured_at": null,
      "min_score": 48.695876476828644,
      "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": 754,
      "rating_method": "sequential_elo",
      "raw_elo": 1739.5911437560183,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 65.3993149417304,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 488
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 872,
      "capped_draws": 10,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.6689649999999999,
        "mean": 0.46799875,
        "median": 0.4352825,
        "min": 0.36661499999999997,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 4.11992
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 58.478968093175965,
      "contributing_entrants": null,
      "distinct_rated_opponents": 436,
      "draws": 190,
      "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": "2026-08-05T05:03:35Z",
      "losses": 218,
      "max_score": 85.08346922744767,
      "measured_at": null,
      "min_score": 32.39551820970374,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 872,
      "rating_method": "sequential_elo",
      "raw_elo": 1671.2669144348458,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 56.782115654344075,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 464
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": 2065,
      "capped_draws": 46,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 54
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.15843093333333336,
        "mean": 0.1253849,
        "median": 0.12730913333333332,
        "min": 0.06204813333333333,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 54
        },
        "recorded_attempt_count": 54,
        "run_count": 24,
        "total": 3.0092376000000005
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 58.330562486741115,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1026,
      "draws": 455,
      "entry_count": 21,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 18,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:56:24Z",
      "losses": 491,
      "max_score": 88.85644622319035,
      "measured_at": null,
      "min_score": 33.28968021864736,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 3,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 0.875,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2051,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.1364625728474,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 3,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 56.41546571640121,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 1105
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 878,
      "capped_draws": 81,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "max": 0.5145615,
        "mean": 0.34875300000000004,
        "median": 0.335163,
        "min": 0.254883,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 2.7900240000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.18181048687466,
      "contributing_entrants": null,
      "distinct_rated_opponents": 437,
      "draws": 277,
      "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": "2026-08-05T06:54:47Z",
      "losses": 219,
      "max_score": 88.04000833669701,
      "measured_at": null,
      "min_score": 17.608657739305404,
      "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": 874,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.0178736706696,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 52.18181048687466,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 378
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 944,
      "capped_draws": 138,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.58673,
        "mean": 0.44285687500000004,
        "median": 0.4176025,
        "min": 0.34269,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.5428550000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 48.92694853208289,
      "contributing_entrants": null,
      "distinct_rated_opponents": 472,
      "draws": 316,
      "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": "2026-08-05T05:26:46Z",
      "losses": 267,
      "max_score": 70.68089553312336,
      "measured_at": null,
      "min_score": 25.033306918921557,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 944,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.196913666888,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 48.92694853208289,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 361
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1296,
      "capped_draws": 65,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 44
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.3888165,
        "mean": 0.26060548125,
        "median": 0.24728879999999998,
        "min": 0.17802225,
        "recorded_attempt_count": 44,
        "run_count": 16,
        "total": 4.169687700000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 50.410518444816546,
      "contributing_entrants": null,
      "distinct_rated_opponents": 649,
      "draws": 375,
      "entry_count": 14,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-08"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:55:12Z",
      "losses": 303,
      "max_score": 83.67694797963125,
      "measured_at": null,
      "min_score": 17.78870942250549,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1296,
      "rating_method": "sequential_elo",
      "raw_elo": 1626.347488636587,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 48.75545089619188,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 618
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 908,
      "capped_draws": 74,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.712055,
        "mean": 0.49864374999999994,
        "median": 0.5065824999999999,
        "min": 0.29423750000000004,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.9891499999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.897011088603556,
      "contributing_entrants": null,
      "distinct_rated_opponents": 452,
      "draws": 291,
      "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": "2026-08-05T06:55:12Z",
      "losses": 240,
      "max_score": 94.87005862041984,
      "measured_at": null,
      "min_score": 17.553436099642553,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 906,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.118740708225,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 46.897011088603556,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 375
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 858,
      "capped_draws": 42,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.244315,
        "mean": 0.178065,
        "median": 0.19681749999999998,
        "min": 0.10277,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.4245200000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.52801384089684,
      "contributing_entrants": null,
      "distinct_rated_opponents": 428,
      "draws": 523,
      "entry_count": 16,
      "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": "2026-08-05T06:57:11Z",
      "losses": 502,
      "max_score": 59.511553845816714,
      "measured_at": null,
      "min_score": 25.99852516396363,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 857,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.7350238553536,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 43.52801384089684,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 566
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 930,
      "capped_draws": 131,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.046574000000000004,
        "mean": 0.036155625000000004,
        "median": 0.035338,
        "min": 0.025803,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 0.315048
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 43.72233320991606,
      "contributing_entrants": null,
      "distinct_rated_opponents": 464,
      "draws": 363,
      "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": "2026-08-05T05:17:39Z",
      "losses": 268,
      "max_score": 65.53875120306154,
      "measured_at": null,
      "min_score": 20.419129829006703,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 928,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.3394240446828,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 42.45366602652019,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 297
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 918,
      "capped_draws": 131,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.34174499999999997,
        "mean": 0.217940625,
        "median": 0.19638,
        "min": 0.14813,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.743525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.28532376648441,
      "contributing_entrants": null,
      "distinct_rated_opponents": 459,
      "draws": 357,
      "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": "2026-08-05T03:49:27Z",
      "losses": 247,
      "max_score": 81.9183167340137,
      "measured_at": null,
      "min_score": 16.591663020618228,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 918,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.8427047975565,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 42.28532376648441,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 314
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 944,
      "capped_draws": 102,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.24673750000000003,
        "mean": 0.16744,
        "median": 0.15809499999999999,
        "min": 0.108735,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 1.3395199999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.424571316358005,
      "contributing_entrants": null,
      "distinct_rated_opponents": 472,
      "draws": 348,
      "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": "2026-08-05T06:54:57Z",
      "losses": 289,
      "max_score": 52.65682323634443,
      "measured_at": null,
      "min_score": 25.620832892368888,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 944,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.7548256127336,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 40.424571316358005,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 307
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 776,
      "capped_draws": 95,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.072978,
        "mean": 0.048872,
        "median": 0.046325000000000005,
        "min": 0.037309999999999996,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.390976
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.180486700957516,
      "contributing_entrants": null,
      "distinct_rated_opponents": 388,
      "draws": 194,
      "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": "2026-08-05T05:17:46Z",
      "losses": 281,
      "max_score": 57.446840898177854,
      "measured_at": null,
      "min_score": 24.604745440205885,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 776,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.6004371597362,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 40.18397074230465,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 301
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 382,
      "capped_draws": 41,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.2996388,
        "mean": 0.13471628689999998,
        "median": 0.1144847257,
        "min": 0.027613287599999998,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 1.0777302952
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.065196543476866,
      "contributing_entrants": null,
      "distinct_rated_opponents": 191,
      "draws": 175,
      "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": "2026-08-05T05:28:30Z",
      "losses": 308,
      "max_score": 66.15885507474644,
      "measured_at": null,
      "min_score": 19.35129652009281,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 382,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.1960904346722,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 40.07668116154651,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 289
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 466,
      "capped_draws": 76,
      "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": 0.43500896000000006
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.51498698617433,
      "contributing_entrants": null,
      "distinct_rated_opponents": 233,
      "draws": 253,
      "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": "2026-08-05T03:48:47Z",
      "losses": 259,
      "max_score": 69.54336053342072,
      "measured_at": null,
      "min_score": 19.793619316293615,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": 0.75,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 466,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.1709934250127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 39.56465347399636,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 268
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": 2758,
      "capped_draws": 325,
      "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": 0.29749325000000004,
        "mean": 0.24155631250000004,
        "median": 0.24021375,
        "min": 0.17873725,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 26
        },
        "run_count": 24,
        "token_priced_attempt_count": 26,
        "total": 5.7973514999999995
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 39.16874370300505,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1377,
      "draws": 947,
      "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": "2026-08-05T06:55:18Z",
      "losses": 963,
      "max_score": 60.20667295526242,
      "measured_at": null,
      "min_score": 22.192579972734823,
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2754,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.498604622192,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.754201302051065,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 844
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 794,
      "capped_draws": 93,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.21477374999999999,
        "mean": 0.17756265624999998,
        "median": 0.17285124999999998,
        "min": 0.1418975,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 1.42050125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.611716088428516,
      "contributing_entrants": null,
      "distinct_rated_opponents": 397,
      "draws": 220,
      "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": "2026-08-05T05:19:06Z",
      "losses": 303,
      "max_score": 57.96187879269228,
      "measured_at": null,
      "min_score": 20.440337873964644,
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 794,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.5045582427992,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.31119254957503,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 271
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 884,
      "capped_draws": 117,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.132112,
        "mean": 0.0780535,
        "median": 0.06797,
        "min": 0.05673,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.6244280000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.446348181834175,
      "contributing_entrants": null,
      "distinct_rated_opponents": 442,
      "draws": 293,
      "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": "2026-08-05T04:04:02Z",
      "losses": 264,
      "max_score": 52.20111840015675,
      "measured_at": null,
      "min_score": 22.62500365197257,
      "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": 884,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.0178904372638,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.1512539673406,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 327
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 808,
      "capped_draws": 103,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 32
        },
        "evidence_basis": "Provider-reported",
        "max": 0.3926418,
        "mean": 0.31750829999999997,
        "median": 0.32150055,
        "min": 0.2298153,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 32
        },
        "recorded_attempt_count": 32,
        "run_count": 16,
        "total": 5.0801327999999994
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 37.13772805268788,
      "contributing_entrants": null,
      "distinct_rated_opponents": 397,
      "draws": 436,
      "entry_count": 32,
      "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": "2026-08-05T06:56:50Z",
      "losses": 438,
      "max_score": 56.503902002777224,
      "measured_at": null,
      "min_score": 19.738580505271273,
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 794,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.73885911828,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 37.13772805268788,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 419
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 452,
      "capped_draws": 6,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.226689264,
        "mean": 0.16037539425,
        "median": 0.140728509,
        "min": 0.10689655,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 1.283003154
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.809027678930654,
      "contributing_entrants": null,
      "distinct_rated_opponents": 226,
      "draws": 213,
      "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": "2026-08-05T05:26:41Z",
      "losses": 262,
      "max_score": 54.35480356946494,
      "measured_at": null,
      "min_score": 20.78553102586511,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 452,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.5960235384453,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 37.04647459414284,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 291
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 528,
      "capped_draws": 68,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.12185499999999999,
        "mean": 0.09110296875000001,
        "median": 0.09280125,
        "min": 0.0343775,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.7288237500000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.11427405995131,
      "contributing_entrants": null,
      "distinct_rated_opponents": 264,
      "draws": 324,
      "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": "2026-08-05T05:35:11Z",
      "losses": 291,
      "max_score": 63.864244753090226,
      "measured_at": null,
      "min_score": 20.42853187574935,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": 0.875,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 528,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.2572018908854,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 36.862914223113556,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 271
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 578,
      "capped_draws": 70,
      "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": 32.35197445455003,
      "contributing_entrants": null,
      "distinct_rated_opponents": 289,
      "draws": 369,
      "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": "2026-08-05T05:34:43Z",
      "losses": 345,
      "max_score": 53.061970706152835,
      "measured_at": null,
      "min_score": 19.32369832555091,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 578,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.0169648040564,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 32.35197445455003,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 266
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 306,
      "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": 36.64777963132047,
      "contributing_entrants": null,
      "distinct_rated_opponents": 152,
      "draws": 95,
      "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": "2026-08-05T03:57:18Z",
      "losses": 224,
      "max_score": 49.01545827784715,
      "measured_at": null,
      "min_score": 24.21197020273949,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 304,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.9344834422477,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 4,
      "repaired_rate": 0.5714285714285714,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 31.863109432351056,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 205
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 831,
      "capped_draws": 139,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00444719,
        "mean": 0.0024656575,
        "median": 0.002155255,
        "min": 0.0011302579999999999,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.019725259999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.58613741833025,
      "contributing_entrants": null,
      "distinct_rated_opponents": 416,
      "draws": 377,
      "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": "2026-08-05T04:12:06Z",
      "losses": 280,
      "max_score": 43.16059564656367,
      "measured_at": null,
      "min_score": 21.765095786368434,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 831,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.9706567381093,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 30.54910799192781,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 174
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 2864,
      "capped_draws": 257,
      "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": 0.02520601875,
        "min": 0.0165820625,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 49
        },
        "run_count": 32,
        "token_priced_attempt_count": 49,
        "total": 0.7792869
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 31.30438245280745,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1430,
      "draws": 728,
      "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": "2026-08-05T06:55:07Z",
      "losses": 1330,
      "max_score": 56.30542073431529,
      "measured_at": null,
      "min_score": 15.510539068363032,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2860,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.4044341064155,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 12,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 29.43083936979678,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 802
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 578,
      "capped_draws": 116,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 21
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.065385,
        "mean": 0.03551179375,
        "median": 0.032728425,
        "min": 0.0200767,
        "recorded_attempt_count": 21,
        "run_count": 9,
        "total": 0.3177278
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 34.035872155662275,
      "contributing_entrants": null,
      "distinct_rated_opponents": 289,
      "draws": 222,
      "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": "2026-08-05T03:41:43Z",
      "losses": 207,
      "max_score": 61.2479202482627,
      "measured_at": null,
      "min_score": 14.05665305055863,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 578,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.1265922885773,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 5,
      "repaired_rate": 0.5555555555555556,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 29.38453059423139,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1004,
      "capped_draws": 86,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.038769960000000006,
        "mean": 0.023744302225,
        "median": 0.0230069837,
        "min": 0.0074361952000000005,
        "recorded_attempt_count": 20,
        "run_count": 9,
        "total": 0.21411433159999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 29.977619677601712,
      "contributing_entrants": null,
      "distinct_rated_opponents": 502,
      "draws": 682,
      "entry_count": 14,
      "failed_game_aliases": [
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:57:10Z",
      "losses": 671,
      "max_score": 41.83782119188973,
      "measured_at": null,
      "min_score": 19.3697810729317,
      "model_code_failure_rate": 0.2222222222222222,
      "model_code_failures": 2,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.7777777777777778,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1004,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.1836553756668,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 7,
      "repaired_rate": 0.7777777777777778,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 28.15211501302235,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 457
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1004,
      "capped_draws": 86,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.038769960000000006,
        "mean": 0.023744302225,
        "median": 0.0230069837,
        "min": 0.0074361952000000005,
        "recorded_attempt_count": 20,
        "run_count": 9,
        "total": 0.21411433159999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 29.977619677601712,
      "contributing_entrants": null,
      "distinct_rated_opponents": 502,
      "draws": 682,
      "entry_count": 16,
      "failed_game_aliases": [
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T03:36:31Z",
      "losses": 671,
      "max_score": 41.83782119188973,
      "measured_at": null,
      "min_score": 19.3697810729317,
      "model_code_failure_rate": 0.2222222222222222,
      "model_code_failures": 2,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.7777777777777778,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1004,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.4993312165873,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 7,
      "repaired_rate": 0.7777777777777778,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 28.15211501302235,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 457
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 452,
      "capped_draws": 56,
      "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": 29.640975194339735,
      "contributing_entrants": null,
      "distinct_rated_opponents": 226,
      "draws": 239,
      "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": "2026-08-05T05:19:01Z",
      "losses": 300,
      "max_score": 45.91779335384322,
      "measured_at": null,
      "min_score": 19.660787526239893,
      "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": 452,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.6650946740144,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 27.584035544377357,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 227
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1163,
      "capped_draws": 194,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 48
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0481474,
        "mean": 0.03800683125,
        "median": 0.037386975,
        "min": 0.02957195,
        "recorded_attempt_count": 48,
        "run_count": 16,
        "total": 0.6081093000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.357331660578332,
      "contributing_entrants": null,
      "distinct_rated_opponents": 581,
      "draws": 452,
      "entry_count": 14,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:55:18Z",
      "losses": 478,
      "max_score": 42.286286758943646,
      "measured_at": null,
      "min_score": 19.020552189812655,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1159,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.084433447604,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 26.459141496199234,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 229
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 586,
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 70
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.103943664,
        "mean": 0.0866474535,
        "median": 0.088847748,
        "min": 0.062759676,
        "recorded_attempt_count": 70,
        "run_count": 16,
        "total": 1.386359256
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.9422064022846,
      "contributing_entrants": null,
      "distinct_rated_opponents": 290,
      "draws": 212,
      "entry_count": 24,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:54:28Z",
      "losses": 449,
      "max_score": 37.8518501101937,
      "measured_at": null,
      "min_score": 11.347553349665287,
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 578,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.8160500613042,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 26.003153051999846,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 8,
      "wins": 271
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 764,
      "capped_draws": 110,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0149315,
        "mean": 0.0101355,
        "median": 0.010566625,
        "min": 0.00402875,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 0.08108399999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 27.748939787173324,
      "contributing_entrants": null,
      "distinct_rated_opponents": 381,
      "draws": 203,
      "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": "2026-08-05T05:18:42Z",
      "losses": 377,
      "max_score": 41.949273557550775,
      "measured_at": null,
      "min_score": 4.666816393696632,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 762,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.2852200609302,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 25.823298200875076,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 182
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 464,
      "capped_draws": 86,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0068074,
        "mean": 0.0034371900000000006,
        "median": 0.00326368,
        "min": 0.00211404,
        "recorded_attempt_count": 35,
        "run_count": 14,
        "total": 0.04917795999999999
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 27.22318762550223,
      "contributing_entrants": null,
      "distinct_rated_opponents": 231,
      "draws": 407,
      "entry_count": 22,
      "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": "2026-08-05T06:54:33Z",
      "losses": 350,
      "max_score": 39.0077721461541,
      "measured_at": null,
      "min_score": 15.67108825376102,
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 462,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.2052004098439,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 4,
      "repaired_rate": 0.2857142857142857,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 25.630385524065343,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 516,
      "capped_draws": 57,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.09705768000000001,
        "mean": 0.0730637925,
        "median": 0.07051098,
        "min": 0.05225028,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.58451034
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 24.860989928116304,
      "contributing_entrants": null,
      "distinct_rated_opponents": 258,
      "draws": 292,
      "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": "2026-08-05T05:18:47Z",
      "losses": 401,
      "max_score": 46.776416361264104,
      "measured_at": null,
      "min_score": 5.922992138645202,
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 516,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.3287371284284,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 7,
      "repaired_rate": 0.875,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 24.04475913093154,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 181
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 344,
      "capped_draws": 11,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.13491350000000002,
        "mean": 0.10247140625000001,
        "median": 0.113468875,
        "min": 0.061553000000000004,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.81977125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 23.578339590965374,
      "contributing_entrants": null,
      "distinct_rated_opponents": 172,
      "draws": 71,
      "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": "2026-08-05T05:35:20Z",
      "losses": 362,
      "max_score": 39.79378137592323,
      "measured_at": null,
      "min_score": 3.5186261065286026,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": 0.625,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.4805040077238,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 20.964437908759642,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 16,
      "attempted_matches": 1498,
      "capped_draws": 366,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 749,
      "draws": 584,
      "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": "2026-07-31T03:35:05Z",
      "losses": 411,
      "max_score": 78.66120174874919,
      "measured_at": null,
      "min_score": 16.341761309376864,
      "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": 1497,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.9837791014288,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 42.74392751708085,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 502
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1308,
      "capped_draws": 237,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 654,
      "draws": 476,
      "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": "2026-07-31T20:22:51Z",
      "losses": 515,
      "max_score": 45.51671696216456,
      "measured_at": null,
      "min_score": 18.666770219098307,
      "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": 1308,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.207774914172,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 30.904388993301325,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 317
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 486,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0711619,
        "mean": 0.039345212500000004,
        "median": 0.033877925,
        "min": 0.02387735,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.3147617
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.82089217872514,
      "contributing_entrants": null,
      "distinct_rated_opponents": 243,
      "draws": 183,
      "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": "2026-08-05T05:11:10Z",
      "losses": 186,
      "max_score": 47.50855231655898,
      "measured_at": null,
      "min_score": 23.408407905328904,
      "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": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.0887334584736,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 29.280763409026072,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 491,
      "capped_draws": 78,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 10,
        "max": 0.11839474,
        "mean": 0.07845433000000002,
        "median": 0.08046371000000001,
        "min": 0.036046930000000005,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 1.2552692799999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 31.81970419489655,
      "contributing_entrants": null,
      "distinct_rated_opponents": 246,
      "draws": 131,
      "entry_count": 6,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:35:25Z",
      "losses": 235,
      "max_score": 58.14658525183732,
      "measured_at": null,
      "min_score": 18.369589094882354,
      "model_code_failure_rate": 0.625,
      "model_code_failures": 10,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.375,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 491,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.3895766010774,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 24.900264188962943,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 298,
      "capped_draws": 9,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 52
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 52,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": 25.282192800215764,
      "contributing_entrants": null,
      "distinct_rated_opponents": 146,
      "draws": 147,
      "entry_count": 12,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.06666666666666667,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:56:13Z",
      "losses": 255,
      "max_score": 43.52220457729294,
      "measured_at": null,
      "min_score": 11.744571555937974,
      "model_code_failure_rate": 0.6,
      "model_code_failures": 9,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": 0.4,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.2635012770018,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": 5,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 20.10618789305667,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-03T20:24:28Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1953.4185734322302,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 88.04000833669701,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 2,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": "2026-08-03T18:12:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1771.292271328763,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 70.43804280002986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 2,
      "wins": 74
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1741.6169869231062,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 67.86856369283086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.8539498938124765,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 99,
      "draws": 53,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1744.3715807356245,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 67.70990700393389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.678927433339865,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-03T16:57:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1726.1208318729848,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 66.0359053103189,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 2,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-03T16:33:33Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1716.9606343725054,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 65.2569227596586,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 2,
      "wins": 66
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 290,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 141,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-08-05T03:52:05Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1715.840502074611,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 64.77698597319846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.948489198165475,
      "unilateral_faults": 4,
      "wins": 177
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-05T00:23:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1666.6223623937797,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 60.58028362371113,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 78,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1647.795835483077,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.87147462359901,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "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": 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": 50,
      "max_score": null,
      "measured_at": "2026-08-05T05:28:30Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1643.003852096852,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.53306464293001,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-08-03T05:37:21Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1566.3794692670535,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.86269605014598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-08-03T09:57:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.3642738682056,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.08179953707419,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 50
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 106,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 53,
      "draws": 92,
      "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": "2026-08-05T05:11:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.028184936769,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.17182865923943,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.815914049854921,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-08-03T09:49:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.3045165513727,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.4326698055027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-08-03T14:22:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.4090782162627,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.31034547609485,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-03T14:29:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.9159537242554,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.24590085260889,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 212,
      "capped_draws": 58,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 106,
      "draws": 58,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.445425050893,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.286286758943646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.622039417435602,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-08-04T20:42:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.891033713489,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.86454300140991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.85345304153558,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T05:35:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.674483808534,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.66078657358321,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 42.71808248423493,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 37,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.6894964558528,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.47617782039243,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.12451556018153,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 354,
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 175,
      "draws": 43,
      "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": 170,
      "max_score": null,
      "measured_at": "2026-08-04T23:06:51Z",
      "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": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.3329076565353,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.290634444481384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.533796253208408,
      "unilateral_faults": 4,
      "wins": 137
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-03T14:21:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.9647599651043,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.027558696955204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 56,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T02:21:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.9213024915678,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.72079315957007,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-08-05T04:12:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.4577652758578,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.175972926108116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-05T03:44:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 26,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.5450833553969,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.0077721461541,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 39.36952453316905,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "capped_draws": 98,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 98,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-07-31T02:06:19Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.431436730129,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.852645783461874,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.417480511718784,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 55,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-07-31T03:18:50Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0411623944224,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.957906696826875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 132,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 66,
      "draws": 22,
      "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": 130,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.0571105645727,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.73684260264018,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.431981136334286,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T05:29:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.4793311113017,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.84315271799331,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-08-05T02:21:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1324.6039580133202,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.1854385334171,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.032850381472425,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-05T04:11:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1307.5635018079774,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.756034767008668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T05:35:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.2033465124364,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.615070134982144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 36,
      "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": "2026-08-05T05:11:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.0654330664993,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.836164490490482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 22.06074898572802,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 442,
      "capped_draws": 82,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 219,
      "draws": 82,
      "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": 284,
      "max_score": null,
      "measured_at": "2026-08-05T03:22:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 438,
      "rating_method": "sequential_elo",
      "raw_elo": 1202.111678705965,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 15.510539068363032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.983045749013221,
      "unilateral_faults": 4,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-04T02:44:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1693.6055326946102,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 66.6442943191533,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 2,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-03T14:22:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1681.6024352152729,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 64.38340087999147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-03T04:42:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.7113348170712,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.52465329657686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "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": 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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:46Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.1451957449874,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.88652077650536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 154,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 77,
      "draws": 100,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T04:14:36Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.0189580640395,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.420195919942806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.24674951880897,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-08-03T03:26:09Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.4533953211321,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.3636679002474,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "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": 152,
      "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": "2026-08-05T04:06:28Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.44121600246,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.99852516396363,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.19101199758159,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 90,
      "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": "2026-08-04T22:25:42Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.2979775705355,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.620832892368888,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 96,
      "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": "2026-08-04T23:30:16Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.6693600787999,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.408407905328904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 91,
      "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": "2026-08-05T01:03:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.89697802721,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.62500365197257,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 314,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 157,
      "draws": 278,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T04:11:58Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.1661517225318,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.192579972734823,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.918254315183693,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 95,
      "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": "2026-08-05T03:21:06Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.2394028782717,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.765095786368434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 108,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.3687742528214,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.78553102586511,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 28,
      "draws": 101,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-03T03:19:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.1598241632423,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.42853187574935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.37199257392821,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "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": 86,
      "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": "2026-08-03T09:30:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.2956909913066,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.419129829006703,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "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": 49,
      "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": "2026-08-05T04:06:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.5534739554275,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.36109221661011,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "draws": 100,
      "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": "2026-08-04T21:01:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.1566233238045,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.793619316293615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 25.383326230453278,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "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": 86,
      "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": "2026-08-05T05:26:46Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.3422066867968,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.738580505271273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 57.19171186957297,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 170,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 85,
      "draws": 270,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-08-03T14:21:40Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.4266020335688,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.3697810729317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 25.734362821941872,
      "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": 2,
      "distinct_rated_opponents": 32,
      "draws": 98,
      "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": "2026-08-03T12:16:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.927138599855,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.32369832555091,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 25.383326230453278,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 287,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 144,
      "draws": 260,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T02:15:28Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 287,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.1689433354313,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.87263301066557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.110614891733731,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 172,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 86,
      "draws": 148,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.388261077859,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.666770219098307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": "2026-08-03T14:15:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.63809611208,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.78870942250549,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 86,
      "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": "2026-08-03T07:00:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.0231648557492,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.553436099642553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 98,
      "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": "2026-08-03T04:41:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.9978015411527,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.498660025504904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "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": 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": 6,
      "max_score": null,
      "measured_at": "2026-08-03T05:47:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.590051762334,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.591663020618228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "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": 83,
      "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": "2026-07-31T03:32:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.35753048828,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.341761309376864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 21,
      "draws": 117,
      "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": "2026-08-05T04:06:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3113488830672,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 15.67108825376102,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 48.77531126230131,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 22,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 11,
      "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": "2026-08-05T01:26:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 22,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.2658829829716,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 15.558477194480595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 50.636316250694534,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "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": 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": 10,
      "max_score": null,
      "measured_at": "2026-08-05T01:19:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.4630623113085,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 11.744571555937974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 42.25107233303306,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 28,
      "draws": 86,
      "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": "2026-08-03T08:16:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.8948469330253,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 9.967521810790636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 25.829556801099734,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 190,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "draws": 8,
      "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": "2026-08-05T04:20:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1904.2815482198878,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 97.66928476084789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.283112930469331,
      "unilateral_faults": 0,
      "wins": 167
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:21:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1637.788138173864,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.14658525183732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 1,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T06:54:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.2983594055843,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.058616923197214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 16,
      "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": "2026-08-05T01:53:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.797238543221,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.3566269308408,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-07-31T02:50:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.5697459219878,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.51671696216456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 20
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 282,
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 141,
      "draws": 130,
      "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": 77,
      "max_score": null,
      "measured_at": "2026-08-05T06:54:33Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.3805631851592,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.52750766968367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.587895361038879,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 78,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 39,
      "draws": 56,
      "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": "2026-08-05T06:55:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.186271761107,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.78232130318044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 46.35134825637578,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "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": 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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.0744357797557,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.420981492242916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 82,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 41,
      "draws": 69,
      "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": "2026-08-05T04:21:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.8677330951837,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.11964378771493,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.951351796455231,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 273,
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 137,
      "draws": 143,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 273,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.6051563726742,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.442561303818024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.534824386604422,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 56,
      "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": "2026-08-05T04:11:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.7736263454274,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.95312226500334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T06:54:28Z",
      "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": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.648879874152,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.172389071472274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 48.41064196554048,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 50,
      "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": "2026-07-31T02:57:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.620482045245,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.82102759332112,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 119,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 60,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 119,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.2197047485586,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.1367649976849,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.666338886355163,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-03T10:31:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.33064839219,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.94213073013162,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-04T22:57:18Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.0203867601301,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.8904510243238,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 59,
      "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": "2026-08-05T06:55:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.7211533982504,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.36280463053722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "capped_draws": 3,
      "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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T06:54:33Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.9321995857717,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.80483322714281,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 35.629606032316254,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 50,
      "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": "2026-08-05T06:55:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.5707786523924,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.421961467653944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T01:53:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.0451235991713,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.109328607264317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-03T12:01:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.5628668819243,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.045539172534085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 31.759688346625158,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T00:30:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.1218657893382,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.840176236683952,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-04T08:55:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.4812698372175,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.26550399898632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 28.430533588759353,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "draws": 36,
      "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": "2026-08-05T04:21:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.16540861595,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.815666165261234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.406681034422945,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-04T22:56:54Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1343.0197207211138,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.71770471751947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:03:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.4398535001199,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.695876476828644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T05:04:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.1647476691362,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.9332689282377,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 240,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.6697759458552,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.830660376507744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.72318795104911,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 234,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 117,
      "draws": 150,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T04:04:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.0156907933451,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.808585407262754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.3097625762757357,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "draws": 63,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.629970640442,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.7928749336898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.187341079842824,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 350,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 175,
      "draws": 231,
      "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": "2026-08-05T05:11:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.0267619373572,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.44018940023784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.39663743638847,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 85,
      "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": "2026-08-05T05:11:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.4642993530238,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.99073310635768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 72,
      "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": "2026-08-05T03:15:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.3585869717513,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.64521003475906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T02:15:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.6000534256289,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.62557494988089,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 252,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 123,
      "draws": 179,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.4132564019528,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.28968021864736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.337553133978721,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 100,
      "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": "2026-08-05T03:15:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.7853187158266,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.82673440407081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 100,
      "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": "2026-08-05T05:03:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.241305078549,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.39551820970374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 74,
      "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": "2026-08-05T04:03:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.187494103844,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.354804347535634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 193,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 96,
      "draws": 155,
      "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": "2026-08-05T05:11:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 189,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.0215300759746,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.75108194933963,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.844126329515209,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 81,
      "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": "2026-08-05T04:04:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.14488539432,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.685761656722633,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "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": 158,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T00:15:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 119,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.1339801476183,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.69438395580862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.849551007159698,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 93,
      "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": "2026-08-04T03:46:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.9113112622058,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.209493257271063,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 2,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 46,
      "draws": 110,
      "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": "2026-08-05T06:56:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.5521886227466,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.207540924358696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 37.757061895277,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 170,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 85,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.2138469305178,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.156444808513356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.19101199758159,
      "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": 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": 4,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.810743470332,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.944136333040866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 107,
      "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": "2026-08-05T03:15:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.5540638545763,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.261376379497502,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "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": 79,
      "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": "2026-08-05T05:03:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.7851670523426,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.353579719814093,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.747146215609725,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T04:04:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.1287926439377,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.500503430901084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.63492938218381,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 99,
      "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": "2026-08-05T03:14:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.9697022578662,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.459132843149533,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 211,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 106,
      "draws": 158,
      "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": "2026-08-05T05:04:07Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 211,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.161344400508,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.126773678453485,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.801966733820217,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 79,
      "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": "2026-08-03T14:28:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.8284045199428,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.033306918921557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 85,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.5159546573475,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.604745440205885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "draws": 99,
      "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": "2026-08-05T03:57:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.3940832357684,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.474165233139676,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.63492938218381,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-04T02:50:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.6340912382486,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.21197020273949,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.26622208392424,
      "unilateral_faults": 2,
      "wins": 10
    },
    {
      "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": 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": 11,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.9162000332021,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.676956043399027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 190,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 95,
      "draws": 260,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-08-05T01:16:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.1427871764781,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.57867696137189,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.8252839883138,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "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": 104,
      "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": "2026-08-05T02:15:10Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.701938811887,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.44671790523425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.664741204687253,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "draws": 91,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-05T01:17:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.6472427180993,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.99855480228331,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.976534673506283,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 28,
      "draws": 74,
      "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": "2026-08-05T06:56:13Z",
      "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.8532139778922,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.203835010961818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.48795150977726,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:55Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.4153901661002,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.01689741998006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 31.996324165557496,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "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": 42,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.817538672456,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 11.347553349665287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 49.59614362960207,
      "unilateral_faults": 8,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 266,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 133,
      "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": "2026-08-05T05:35:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1961.7749539008435,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 82.88602996661304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 236
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 180,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 90,
      "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": "2026-08-05T05:25:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1811.3147558011215,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 69.79149227763016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 318,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 159,
      "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": "2026-08-05T05:26:36Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1775.7285813884528,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 67.06621443748418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.587275524205726,
      "unilateral_faults": 0,
      "wins": 229
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1763.8599969928403,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 66.26529025688052,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-03T13:20:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1717.0927003529362,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 62.411231853726754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:01:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1691.8487318885484,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 60.437208079044204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:41:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.4694531265427,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.14727397018848,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:51:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.976425086682,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.10379418968867,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 44,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.9703793474673,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.061970706152835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.29717474536497,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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": "2026-08-05T03:41:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.5335585643102,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.65682323634443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.6015854557863,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.59419174705676,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.384199623850844,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 99,
      "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": 105,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.0007086934363,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.33642397618402,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.2668860824478045,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:01:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1592.574318717706,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.20111840015675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:42:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.0136054414809,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.39508357270537,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 47,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.6588656258828,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.73802589876419,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.239599789301113,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1566.1873360530612,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.01545827784715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.287101294886725,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 62,
      "max_score": null,
      "measured_at": "2026-08-05T03:49:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.5784583726859,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.80361235858553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-08-05T03:00:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.122545035995,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.59284136341126,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.64065622904072,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:49:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.4801116415908,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.50855231655898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:53:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.0016338263567,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.37246936992358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.5598581168831473,
      "unilateral_faults": 0,
      "wins": 121
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 78,
      "max_score": null,
      "measured_at": "2026-08-05T05:25:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.7373353693486,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.55395008692883,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-05T02:08:23Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.9643907366299,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.91779335384322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.180881873546443,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-05T04:51:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.2714896969158,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.45963078171682,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 60,
      "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": 97,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.0851080733141,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.42181568717994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 25.554665212036397,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-08-05T01:10:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.5598725581976,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.16059564656367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 418,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 209,
      "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": 224,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:06Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 418,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.0659044162278,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.16950375360156,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 194
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 60,
      "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": 111,
      "max_score": null,
      "measured_at": "2026-08-05T05:25:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.8691016822452,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.8518501101937,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 29.341193710595128,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 496,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 248,
      "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": 294,
      "max_score": null,
      "measured_at": "2026-08-05T04:42:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 496,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.1825662737183,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.68541016863408,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.3157835475016277,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 158,
      "max_score": null,
      "measured_at": "2026-08-04T22:17:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1376.9153252902406,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.32866694206213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.04969343305294,
      "unilateral_faults": 0,
      "wins": 128
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 61,
      "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": 144,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.1260289908478,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.999553826228972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 22.838796696547423,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-08-05T03:42:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.0855540317798,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.195666678862878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.717338510322858,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 119,
      "max_score": null,
      "measured_at": "2026-07-31T03:33:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1307.71554307816,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.266873714533958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.815914049854921,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "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": 98,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:25Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1295.4437942097927,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.78924812766465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 176,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 88,
      "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": 128,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1283.6228237197265,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.9737881632984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "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": 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": "2026-08-04T09:17:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1279.0180447312632,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.956093569257188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.82750658264339,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-08-04T21:09:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1234.4309794055496,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.28851435525645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "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": 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": 117,
      "max_score": null,
      "measured_at": "2026-08-04T23:59:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1050.902463188506,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 5.922992138645202,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.4544298291952,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-08-03T14:55:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1955.8803057155433,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 94.87005862041984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:50Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1868.8044414067544,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 86.64377257189392,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T02:41:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1851.262045065243,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 85.08346922744767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 168,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T06:54:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1841.5133446168375,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 83.67694797963125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 132
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T00:51:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.5613422611286,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 81.9183167340137,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T03:41:17Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1806.124039833382,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 80.83296452654382,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 89,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-07-31T02:45:11Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1787.4376165902647,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 78.66120174874919,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.957067918206963,
      "unilateral_faults": 0,
      "wins": 107
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-08-04T23:37:14Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.6031514919032,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 69.54336053342072,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.517288899732886,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 217,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:24Z",
      "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": 217,
      "rating_method": "sequential_elo",
      "raw_elo": 1657.1298506300159,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 66.59262070172484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.402236279499051,
      "unilateral_faults": 0,
      "wins": 121
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-03T07:34:03Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1662.1296966917387,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 66.15885507474644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.007326216468247,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-03T10:50:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": 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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1642.207296864758,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 65.53875120306154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T03:41:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.4018687999608,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 61.2479202482627,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "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": 109,
      "max_score": null,
      "measured_at": "2026-08-05T01:53:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.5913398799398,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 60.20667295526242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9885453854133264,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 1,
      "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": 16,
      "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": "2026-08-05T05:35:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.03231877175,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.92689918058069,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.742063492063494,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.9370321371216,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.51235426034554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 64,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-08-05T06:54:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.8482780083127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.503902002777224,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 28.83387508077879,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 490,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 245,
      "draws": 31,
      "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": 232,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 490,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.721116470262,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.30542073431529,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.4685987893416486,
      "unilateral_faults": 0,
      "wins": 227
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.3048803307256,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.22200846259964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "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": 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": 98,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.3452760559187,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.57943316939411,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.4772197274317325,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T06:54:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.508649868163,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.60384576894331,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-08-03T09:49:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.0649919553914,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.87158633438607,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T03:56:30Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.3657683124545,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.98896150615873,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-08-03T10:58:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.3978131432787,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.949273557550775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-08-03T12:10:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.6428600108695,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.92205480031329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.748827762211599,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 135,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": 88,
      "max_score": null,
      "measured_at": "2026-08-04T20:06:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 135,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.5848235187086,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.38276681114314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 54,
      "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": 108,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.7633259115487,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.49351604319952,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 31.06128752274429,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "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": 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": 85,
      "max_score": null,
      "measured_at": "2026-08-05T04:57:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.3252491367793,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.540674524591545,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.237183532345085,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "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": 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": 86,
      "max_score": null,
      "measured_at": "2026-08-03T13:20:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1324.5664254277772,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.10425107444389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.28737186011545,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "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": 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": 91,
      "max_score": null,
      "measured_at": "2026-08-05T01:46:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.550618114029,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.51820706435848,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.237183532345085,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-08-04T23:37:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.7411627604797,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.375875386655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "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": 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": 60,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.0576365585443,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.958777248863868,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 28.08463570631327,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "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": 117,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.102135627474,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.274718681120902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.823251170389485,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.5021457048715,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.325282721903957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 25.829556801099734,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "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": 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": 88,
      "max_score": null,
      "measured_at": "2026-08-05T02:42:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1263.978424801378,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.167965147210907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.747146215609725,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "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": 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": 81,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1236.8582485470383,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.357692904131554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 22.864786698060648,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 81,
      "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": 132,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1160.9615169384278,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.020552189812655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.468842775200363,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 244,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 122,
      "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": "2026-08-05T05:26:27Z",
      "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": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1940.4116114258877,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 85.63226983764412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.8539498938124765,
      "unilateral_faults": 0,
      "wins": 205
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:27:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1773.1661991465724,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 70.68089553312336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "2026-08-05T04:28:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.9902710692518,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 69.30390855095736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 204,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 71,
      "max_score": null,
      "measured_at": "2026-08-05T04:30:53Z",
      "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": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1725.4022170469711,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 66.11484875005729,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.79454145484633,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 288,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 144,
      "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": 107,
      "max_score": null,
      "measured_at": "2026-07-31T03:29:12Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1720.1848392389459,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 65.68010929815331,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.033231573004961,
      "unilateral_faults": 0,
      "wins": 181
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T02:27:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1714.4239416868895,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 63.864244753090226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 25.38990374359382,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-08-05T01:31:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1683.4145361717362,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 62.84516887775912,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "2026-08-04T22:40:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1666.4268161629404,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 61.361579256614846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.8152809272333,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.11004723437738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-08-05T04:28:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1628.4297641341607,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.96187879269228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.3477234865395,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.446840898177854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 232,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "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": 98,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:37Z",
      "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": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.7216538502953,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.99731786762054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.566064997422586,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.2909691339737,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.65363080364732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "2026-08-05T04:34:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.4430409822883,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.41140792271331,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 44,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.7598223575376,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.64490710852141,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.017746625155496,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "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": 60,
      "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": "2026-08-05T06:57:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.0991425629509,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.776272775313714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.9176862481661074,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-05T03:28:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.5918102941107,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.58530359916948,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 393,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 196,
      "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": 216,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:27Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 393,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.5687273778033,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.13494994625827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.12514876054421956,
      "unilateral_faults": 0,
      "wins": 177
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:34:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.9713046631996,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.776416361264104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.080592941617738,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.2719353363145,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.359421410539206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.724920543044455,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 113,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.2957378785,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.52220457729294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 25.288270414847073,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-03T15:18:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.0315415173136,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.3549780388027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.386417506374595,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.775336915899,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.97118928762754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 118,
      "max_score": null,
      "measured_at": "2026-08-04T23:37:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.2899833942533,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.83782119188973,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.488310255185098,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 1,
      "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": 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": 69,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.7290822266407,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.83692106824891,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.54985278838047,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "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": 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": "2026-08-05T00:37:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.4833878281063,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.79378137592323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.74936409813348,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "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": 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": "2026-08-04T21:46:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.3500810499045,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.25943897025135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.85345304153558,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 190,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "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": 115,
      "max_score": null,
      "measured_at": "2026-07-31T03:07:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.8724654180028,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.16873173236723,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.283112930469331,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 96,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.6835123650214,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.721339092090396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 36.16857499447537,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 52,
      "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": 113,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.7115581527555,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.215324657126956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.94927125227558,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "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": 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": "2026-08-05T01:38:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.427688695992,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.47064359767043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.12451556018153,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 457,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 228,
      "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": 318,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 457,
      "rating_method": "sequential_elo",
      "raw_elo": 1285.053507576868,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.32895163665409,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.9010645474206243,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T05:19:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1253.5544921999174,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.992806942856724,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T05:26:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1190.757908767719,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.369589094882354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-08-04T23:43:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1136.958953317386,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 14.05665305055863,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "2026-08-05T01:39:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1030.1908334918917,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 4.666816393696632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 348,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 174,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-05T02:34:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 348,
      "rating_method": "sequential_elo",
      "raw_elo": 1959.177771791579,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 88.85644622319035,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.4885350752759137,
      "unilateral_faults": 0,
      "wins": 304
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 262,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 131,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1897.8126562352456,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 82.16198499155695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 216
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1854.8373059774533,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 76.98336681634814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-08-03T08:03:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1785.981513065026,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 69.11838234678588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "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": 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": 63,
      "max_score": null,
      "measured_at": "2026-08-04T21:52:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1701.9630242155704,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 59.511553845816714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.2943419813913195,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T01:31:37Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1667.5092199905735,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.35480356946494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.22027992219475,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 11,
      "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": "2026-08-05T05:18:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1651.8394288276704,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.05623433107263,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-02T22:46:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.6942987321636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.91606278892348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 380,
      "capped_draws": 170,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 190,
      "draws": 170,
      "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": 114,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.9622489746218,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.20581487904527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.3313144022682706,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T03:28:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.332639053323,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.25142205084722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "capped_draws": 70,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 65,
      "draws": 110,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:47Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.5107778326746,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.57155276802534,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 29.974048701260934,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-03T12:36:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.7534965706259,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.039349146950016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-03T06:08:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.4436413007966,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.985519854727933,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 156,
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.8590805710878,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.65874799969496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "capped_draws": 105,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 70,
      "draws": 105,
      "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": "2026-08-05T03:33:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.5477969238084,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.53729144867848,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 99,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 99,
      "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": "2026-08-05T03:33:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.861164888524,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.31922167829491,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 304,
      "capped_draws": 249,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 152,
      "draws": 249,
      "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": "2026-07-31T03:35:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 303,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.623772094612,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.101805618887024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.765621052642042,
      "unilateral_faults": 1,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 104,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "draws": 104,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.1245896868447,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.09490742966929,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 408,
      "capped_draws": 239,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 204,
      "draws": 239,
      "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": 108,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 408,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.6318876144662,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.47285784764608,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "capped_draws": 102,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 102,
      "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": "2026-08-04T23:29:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.747777600697,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.892763334314395,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 42,
      "draws": 92,
      "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": "2026-08-05T01:39:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.2111834594807,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.797657036523127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.913534972537988,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 44,
      "draws": 116,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T00:36:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.2115047229668,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.57813859269058,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.090087987331263,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 92,
      "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": "2026-08-05T01:39:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.8948685173345,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.513431403839135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 41,
      "draws": 106,
      "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": "2026-08-05T05:18:47Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.249176342982,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.15585015743753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.804373924048683,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "capped_draws": 79,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 52,
      "draws": 151,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0487153291788,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.103391256384768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 81,
      "capped_draws": 61,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 61,
      "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": "2026-08-05T05:25:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 81,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.0575438734552,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.825513643960814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.465763037423269,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "capped_draws": 181,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 181,
      "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": "2026-07-31T03:35:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.0566857622682,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.706437896899708,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.280733777820661,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 41,
      "draws": 105,
      "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": "2026-08-05T03:27:52Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.3196679470848,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.653180799629084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.698067098122827,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "capped_draws": 128,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 81,
      "draws": 128,
      "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": "2026-08-05T05:26:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.7950522422157,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.11024043322827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.542957485854352,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 152,
      "capped_draws": 80,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 76,
      "draws": 125,
      "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": 91,
      "max_score": null,
      "measured_at": "2026-08-04T21:46:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.6463544370927,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.450874447724814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.94665204376684,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 98,
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 49,
      "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": 77,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.6641089407344,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.450319954890443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 46.82927958473947,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 69,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.8995387907771,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.440337873964644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 39,
      "draws": 98,
      "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": "2026-08-05T04:28:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1361.4513228516012,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.660787526239893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.091483237436318,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "draws": 89,
      "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": "2026-08-04T08:41:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.055533810906,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.35129652009281,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.517288899732886,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-03T02:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.54682570675,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.608657739305404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "draws": 16,
      "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": 89,
      "max_score": null,
      "measured_at": "2026-08-05T02:33:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1221.5615690949933,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 3.5186261065286026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.63492938218381,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1742,
      "capped_draws": 132,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.5221625,
        "mean": 0.2856328125,
        "median": 0.2536225,
        "min": 0.2178175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 4.570125
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 69.78432167559475,
      "contributing_entrants": null,
      "distinct_rated_opponents": 867,
      "draws": 383,
      "entry_count": 14,
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:33:34Z",
      "losses": 289,
      "max_score": 96.50163167645941,
      "measured_at": null,
      "min_score": 46.570204853782045,
      "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": 1741,
      "rating_method": "sequential_elo",
      "raw_elo": 1773.4635471348022,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 67.49317749038875,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1069
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 906,
      "capped_draws": 97,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.15985749999999999,
        "mean": 0.09356500000000001,
        "median": 0.07461,
        "min": 0.06826499999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.74852
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.09900592574367,
      "contributing_entrants": null,
      "distinct_rated_opponents": 447,
      "draws": 341,
      "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": "2026-08-05T05:41:54Z",
      "losses": 184,
      "max_score": 97.55488190852645,
      "measured_at": null,
      "min_score": 19.60034070265804,
      "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": 900,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.0120678828102,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 50.09900592574367,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 375
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 948,
      "capped_draws": 109,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.144235,
        "mean": 0.12174125,
        "median": 0.121475,
        "min": 0.09594,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.9739299999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 45.30926050948271,
      "contributing_entrants": null,
      "distinct_rated_opponents": 473,
      "draws": 329,
      "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": "2026-08-05T05:02:30Z",
      "losses": 263,
      "max_score": 64.91944958274557,
      "measured_at": null,
      "min_score": 25.69560465698689,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 948,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.244847449798,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 45.30926050948271,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 356
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 1032,
      "capped_draws": 103,
      "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,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 17
        },
        "recorded_attempt_count": 17,
        "run_count": 16,
        "total": 1.1192034
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 43.84198067135024,
      "contributing_entrants": null,
      "distinct_rated_opponents": 516,
      "draws": 477,
      "entry_count": 32,
      "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": "2026-08-05T06:56:40Z",
      "losses": 441,
      "max_score": 62.82646209967631,
      "measured_at": null,
      "min_score": 17.703162245681458,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 1.0,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1032,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.8327117008246,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 43.84198067135024,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 710
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 786,
      "capped_draws": 28,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.190125,
        "mean": 0.15785312499999998,
        "median": 0.15388000000000002,
        "min": 0.131495,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.2628249999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.39353927490981,
      "contributing_entrants": null,
      "distinct_rated_opponents": 391,
      "draws": 198,
      "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": "2026-08-05T03:47:33Z",
      "losses": 246,
      "max_score": 68.98590691472927,
      "measured_at": null,
      "min_score": 17.488893388132354,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 786,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.0231928444312,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 42.93601992202062,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 342
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 888,
      "capped_draws": 50,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.147405,
        "mean": 0.12146437500000001,
        "median": 0.124865,
        "min": 0.09045,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 1.069485
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 43.37417866830484,
      "contributing_entrants": null,
      "distinct_rated_opponents": 440,
      "draws": 237,
      "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": "2026-08-05T05:17:02Z",
      "losses": 293,
      "max_score": 59.006818274433016,
      "measured_at": null,
      "min_score": 29.15647522370581,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 882,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.2154838477545,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 42.11561369605062,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 352
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 868,
      "capped_draws": 80,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.11634299999999999,
        "mean": 0.07787519999999999,
        "median": 0.0843883,
        "min": 0.041110400000000005,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 28
        },
        "recorded_attempt_count": 28,
        "run_count": 16,
        "total": 1.2460031999999999
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 42.02398603997369,
      "contributing_entrants": null,
      "distinct_rated_opponents": 434,
      "draws": 391,
      "entry_count": 30,
      "failed_game_aliases": [
        "GB2-04"
      ],
      "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": "2026-08-05T06:56:18Z",
      "losses": 372,
      "max_score": 61.644694598987854,
      "measured_at": null,
      "min_score": 16.238936021776848,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 0.9375,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 868,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.9368813771428,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 41.35138523603543,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 583
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 1042,
      "capped_draws": 248,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 1,
          "local_list_price_estimate": 8,
          "provider_dashboard_reconciled": 1
        },
        "evidence_basis": "Mixed: Provider-reported + Recorded attempt + Standard list-price estimate",
        "max": 0.07806,
        "mean": 0.062955625,
        "median": 0.061544,
        "min": 0.049788,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "recorded_attempt_count": 2,
        "run_count": 9,
        "token_priced_attempt_count": 8,
        "total": 0.57987
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 40.65157086620186,
      "contributing_entrants": null,
      "distinct_rated_opponents": 518,
      "draws": 468,
      "entry_count": 9,
      "failed_game_aliases": [],
      "first_pass_admitted": 9,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:08Z",
      "losses": 275,
      "max_score": 57.99889288812461,
      "measured_at": null,
      "min_score": 24.09530085961754,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1042,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.647139762114,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 40.65157086620186,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 299
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 932,
      "capped_draws": 138,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.1192425,
        "mean": 0.0683559375,
        "median": 0.06152125,
        "min": 0.0542775,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 0.6063374999999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 39.69550753752692,
      "contributing_entrants": null,
      "distinct_rated_opponents": 462,
      "draws": 363,
      "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": "2026-08-05T03:05:30Z",
      "losses": 296,
      "max_score": 52.63127668910358,
      "measured_at": null,
      "min_score": 28.273880023544745,
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 930,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.8160766249243,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.54368456643071,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 271
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 818,
      "capped_draws": 138,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.03912625,
        "mean": 0.022799843750000003,
        "median": 0.021642500000000002,
        "min": 0.015285,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.18239874999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.493085531119945,
      "contributing_entrants": null,
      "distinct_rated_opponents": 401,
      "draws": 281,
      "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": "2026-08-05T05:33:39Z",
      "losses": 272,
      "max_score": 68.55479086064098,
      "measured_at": null,
      "min_score": 22.482461561801962,
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 812,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.9753327208534,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.19645684579572,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 259
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 830,
      "capped_draws": 161,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.029078938,
        "mean": 0.015562441375000001,
        "median": 0.013116718500000001,
        "min": 0.005612805,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.12449953100000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.82358458571298,
      "contributing_entrants": null,
      "distinct_rated_opponents": 408,
      "draws": 289,
      "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": "2026-08-05T04:27:08Z",
      "losses": 266,
      "max_score": 67.31147896345796,
      "measured_at": null,
      "min_score": 17.2055412078098,
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 830,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.7125262755892,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 37.548936814743556,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 275
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 686,
      "capped_draws": 50,
      "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": 38.62762612577164,
      "contributing_entrants": null,
      "distinct_rated_opponents": 340,
      "draws": 175,
      "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": "2026-08-05T05:17:07Z",
      "losses": 254,
      "max_score": 52.11814186315531,
      "measured_at": null,
      "min_score": 25.43537970074668,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 1,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": 0.8571428571428571,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 686,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.4598024034094,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.2857142857142857,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 37.167326419101414,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 257
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 934,
      "capped_draws": 107,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.09459400000000001,
        "mean": 0.0571955,
        "median": 0.043012,
        "min": 0.032534,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 0.457564
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.39316993293499,
      "contributing_entrants": null,
      "distinct_rated_opponents": 463,
      "draws": 324,
      "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": "2026-08-05T05:41:31Z",
      "losses": 336,
      "max_score": 56.63398289929676,
      "measured_at": null,
      "min_score": 14.75877111394388,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 933,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.6731004328792,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 36.39316993293499,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 273
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1476,
      "capped_draws": 310,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.00407402,
        "mean": 0.0029986699999999997,
        "median": 0.00314426,
        "min": 0.0012446800000000002,
        "recorded_attempt_count": 33,
        "run_count": 14,
        "total": 0.04176386
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 37.41625726018497,
      "contributing_entrants": null,
      "distinct_rated_opponents": 719,
      "draws": 510,
      "entry_count": 12,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:40:59Z",
      "losses": 500,
      "max_score": 52.809153048377176,
      "measured_at": null,
      "min_score": 21.571994896490278,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 2,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": 0.8571428571428571,
      "provider": "Other",
      "provider_key": "other",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1465,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.326306325724,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 5,
      "repaired_rate": 0.35714285714285715,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 36.00175279843416,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 455
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 544,
      "capped_draws": 120,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.0222516,
        "mean": 0.01697319375,
        "median": 0.015739925000000002,
        "min": 0.012759,
        "recorded_attempt_count": 34,
        "run_count": 16,
        "total": 0.27157109999999995
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.569696137032814,
      "contributing_entrants": null,
      "distinct_rated_opponents": 271,
      "draws": 476,
      "entry_count": 30,
      "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": "2026-08-05T05:41:49Z",
      "losses": 403,
      "max_score": 58.42525560215735,
      "measured_at": null,
      "min_score": 16.907630545609305,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.9375,
      "provider": "Google",
      "provider_key": "google",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 542,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.4671465202425,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 35.98439213949794,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 346
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 844,
      "capped_draws": 218,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.156555,
        "mean": 0.1422525,
        "median": 0.14850249999999998,
        "min": 0.12078,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.13802
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.189039884034734,
      "contributing_entrants": null,
      "distinct_rated_opponents": 417,
      "draws": 432,
      "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": "2026-08-05T05:23:57Z",
      "losses": 213,
      "max_score": 51.11478815980904,
      "measured_at": null,
      "min_score": 23.30438447793437,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 844,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.0171483481488,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 35.968057141237665,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 633,
      "capped_draws": 133,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "evidence_basis": "Provider-reported",
        "max": 0.07826175,
        "mean": 0.05584070625,
        "median": 0.0541695,
        "min": 0.0411735,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 0.8934513000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 35.192117790614326,
      "contributing_entrants": null,
      "distinct_rated_opponents": 313,
      "draws": 568,
      "entry_count": 32,
      "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": "2026-08-05T06:56:02Z",
      "losses": 413,
      "max_score": 51.56860730824784,
      "measured_at": null,
      "min_score": 15.356957668247802,
      "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": 626,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.3736824777882,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 35.192117790614326,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 380
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 720,
      "capped_draws": 42,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.09803328,
        "mean": 0.0253809975,
        "median": 0.00943521,
        "min": 0.00639384,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.20304798000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.27597496645672,
      "contributing_entrants": null,
      "distinct_rated_opponents": 358,
      "draws": 170,
      "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": "2026-08-05T04:33:21Z",
      "losses": 266,
      "max_score": 49.2908922032663,
      "measured_at": null,
      "min_score": 17.49414607975783,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 720,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.8610454137633,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 34.68920343155285,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 284
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 684,
      "capped_draws": 131,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.001632522,
        "mean": 0.00126739675,
        "median": 0.001232095,
        "min": 0.00090937,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.010139173999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.3872173535151,
      "contributing_entrants": null,
      "distinct_rated_opponents": 336,
      "draws": 307,
      "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": "2026-08-05T05:08:37Z",
      "losses": 178,
      "max_score": 72.251918530255,
      "measured_at": null,
      "min_score": 13.313054666786927,
      "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": 678,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.5629379610066,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 32.93151641928329,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 193
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1462,
      "capped_draws": 132,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0721503,
        "mean": 0.03677837187500001,
        "median": 0.0324098875,
        "min": 0.01945095,
        "recorded_attempt_count": 39,
        "run_count": 16,
        "total": 0.5884539500000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 34.48501987666433,
      "contributing_entrants": null,
      "distinct_rated_opponents": 715,
      "draws": 468,
      "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": "2026-08-05T05:41:54Z",
      "losses": 569,
      "max_score": 62.96894118841835,
      "measured_at": null,
      "min_score": 17.986293369286603,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1461,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.989123005506,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 32.09192706345631,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 424
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1884,
      "capped_draws": 258,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0097359,
        "mean": 0.0038356840999999994,
        "median": 0.0020557588,
        "min": 0.0014804776,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.030685472800000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.33105017629488,
      "contributing_entrants": null,
      "distinct_rated_opponents": 937,
      "draws": 555,
      "entry_count": 17,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:45Z",
      "losses": 738,
      "max_score": 48.233162638067576,
      "measured_at": null,
      "min_score": 20.22265746079894,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.75,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1882,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.4549430232298,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 31.948642112138007,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 589
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1728,
      "capped_draws": 352,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 38
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.021206376000000002,
        "mean": 0.01337795025,
        "median": 0.01381146,
        "min": 0.006392298,
        "recorded_attempt_count": 38,
        "run_count": 16,
        "total": 0.21404720400000002
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 32.92807444254993,
      "contributing_entrants": null,
      "distinct_rated_opponents": 842,
      "draws": 622,
      "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": "2026-08-05T05:41:26Z",
      "losses": 645,
      "max_score": 48.45429450824968,
      "measured_at": null,
      "min_score": 13.789037064172394,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1724,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.3765675707743,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 31.84698682175468,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 457
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 2895,
      "capped_draws": 476,
      "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-2026-07-30": 56
        },
        "run_count": 32,
        "token_priced_attempt_count": 56,
        "total": 0.28794675000000003
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 31.371594744143064,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1426,
      "draws": 1130,
      "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": "2026-08-05T05:41:31Z",
      "losses": 1053,
      "max_score": 56.65051046409322,
      "measured_at": null,
      "min_score": 19.59118479048314,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2888,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.9585326737122,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 15,
      "repaired_rate": 0.46875,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 29.494029057469312,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 705
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 2773,
      "capped_draws": 401,
      "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-2026-07-30": 29
        },
        "run_count": 24,
        "token_priced_attempt_count": 29,
        "total": 0.4149345
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 28.626949132145135,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1367,
      "draws": 1133,
      "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": "2026-08-05T05:33:34Z",
      "losses": 1021,
      "max_score": 39.007466418277744,
      "measured_at": null,
      "min_score": 16.762689788970278,
      "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": 2766,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.2054971572938,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333334,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 28.626949132145135,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 7,
      "wins": 612
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 2170,
      "capped_draws": 348,
      "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": 0.0018257240000000001,
        "recorded_attempt_count": 34,
        "run_count": 24,
        "total": 0.053353921299999996
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 30.337491687517996,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1073,
      "draws": 868,
      "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": "2026-08-05T05:41:49Z",
      "losses": 797,
      "max_score": 40.791267003138834,
      "measured_at": null,
      "min_score": 21.33030113424673,
      "model_code_failure_rate": 0.20833333333333334,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2170,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.1868857638447,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333334,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 28.616417290149574,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 505
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 746,
      "capped_draws": 146,
      "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": 29.708758518921826,
      "contributing_entrants": null,
      "distinct_rated_opponents": 365,
      "draws": 240,
      "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": "2026-08-05T03:48:11Z",
      "losses": 302,
      "max_score": 41.22577138332814,
      "measured_at": null,
      "min_score": 19.625108861534393,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 744,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.5128996597357,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.14285714285714285,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 28.585632515541217,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 202
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 677,
      "capped_draws": 28,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0154064,
        "mean": 0.00874386,
        "median": 0.0064215999999999995,
        "min": 0.00524064,
        "recorded_attempt_count": 13,
        "run_count": 9,
        "total": 0.08145696000000001
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 27.21481384964496,
      "contributing_entrants": null,
      "distinct_rated_opponents": 333,
      "draws": 224,
      "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": "2026-08-05T03:19:33Z",
      "losses": 299,
      "max_score": 47.34237964243975,
      "measured_at": null,
      "min_score": 10.523618948427423,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 675,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.117531201974,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 24.591360322408136,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 152
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 448,
      "capped_draws": 62,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.0032939400000000004,
        "mean": 0.0016413085000000001,
        "median": 0.0014119655,
        "min": 0.00045831,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.013130468
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 24.79487793327039,
      "contributing_entrants": null,
      "distinct_rated_opponents": 224,
      "draws": 160,
      "entry_count": 14,
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:57:15Z",
      "losses": 349,
      "max_score": 41.569177511800305,
      "measured_at": null,
      "min_score": 9.425383107713568,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 448,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.9808781548832,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 23.980817711208037,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 1582,
      "capped_draws": 448,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 40
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 40,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 25.94707410067487,
      "contributing_entrants": null,
      "distinct_rated_opponents": 636,
      "draws": 825,
      "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": "2026-08-05T05:41:59Z",
      "losses": 510,
      "max_score": 38.9946317420071,
      "measured_at": null,
      "min_score": 17.149445622957767,
      "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": 1578,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.254695962745,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 23.070573811992162,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 243
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 899,
      "capped_draws": 141,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.038815,
        "mean": 0.02196775,
        "median": 0.0196975,
        "min": 0.016152,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.17574200000000004
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 19.914859222537768,
      "contributing_entrants": null,
      "distinct_rated_opponents": 442,
      "draws": 376,
      "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": "2026-08-05T05:41:40Z",
      "losses": 416,
      "max_score": 36.47520283021661,
      "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": 893,
      "rating_method": "sequential_elo",
      "raw_elo": 1283.7887205375928,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 19.914859222537768,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 3,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "capped_draws": 30,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 1,
        "cost_basis_counts": {
          "estimated": 1,
          "local_standard_estimate": 1
        },
        "evidence_basis": "Mixed: Recorded attempt + Standard list-price estimate",
        "max": 0.0023425,
        "mean": 0.0023425,
        "median": 0.0023425,
        "min": 0.0023425,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 1,
          "boardgame-list-prices-2026-07-30": 1
        },
        "recorded_attempt_count": 1,
        "run_count": 1,
        "token_priced_attempt_count": 1,
        "total": 0.0023425
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": 39.478292990152276,
      "contributing_entrants": null,
      "distinct_rated_opponents": 49,
      "draws": 30,
      "entry_count": 1,
      "failed_game_aliases": [],
      "first_pass_admitted": 1,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:27:30Z",
      "losses": 32,
      "max_score": 39.478292990152276,
      "measured_at": null,
      "min_score": 39.478292990152276,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.1194224909668,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Reasoning field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 39.478292990152276,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": 2578,
      "capped_draws": 166,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1289,
      "draws": 757,
      "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": "2026-07-31T20:23:06Z",
      "losses": 946,
      "max_score": 54.257859859863686,
      "measured_at": null,
      "min_score": 17.84653261324441,
      "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": 2578,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.6866641670401,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.46013834265657,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 875
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 642,
      "capped_draws": 119,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 321,
      "draws": 228,
      "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": "2026-07-31T03:28:04Z",
      "losses": 254,
      "max_score": 53.4061534092432,
      "measured_at": null,
      "min_score": 12.693314222369741,
      "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": 642,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.9395847805426,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 32.9209508641027,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 240,
      "capped_draws": 49,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.03772852,
        "mean": 0.024905897500000003,
        "median": 0.026095300000000002,
        "min": 0.00984735,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.19924718
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.94089777477116,
      "contributing_entrants": null,
      "distinct_rated_opponents": 118,
      "draws": 67,
      "entry_count": 8,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:57:11Z",
      "losses": 155,
      "max_score": 53.50967288140359,
      "measured_at": null,
      "min_score": 23.170311606444997,
      "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": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.9332382654093,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 31.063468515058986,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 132
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 228,
      "capped_draws": 74,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 8,
          "local_standard_estimate": 13
        },
        "evidence_basis": "Mixed: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.17217,
        "mean": 0.11039474999999999,
        "median": 0.10846,
        "min": 0.07562,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 13,
          "boardgame-list-prices-2026-07-30": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "token_priced_attempt_count": 13,
        "total": 0.8831579999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.47551028903298,
      "contributing_entrants": null,
      "distinct_rated_opponents": 114,
      "draws": 123,
      "entry_count": 8,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:08Z",
      "losses": 160,
      "max_score": 45.42172085598957,
      "measured_at": null,
      "min_score": 24.48313253075837,
      "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": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.7538901877429,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 27.308540185582956,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 800,
      "capped_draws": 119,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 36
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.215758025,
        "mean": 0.16162675,
        "median": 0.1594081875,
        "min": 0.098579625,
        "recorded_attempt_count": 36,
        "run_count": 16,
        "total": 2.5860279999999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 32.49225562048957,
      "contributing_entrants": null,
      "distinct_rated_opponents": 394,
      "draws": 360,
      "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": "2026-08-05T04:41:06Z",
      "losses": 241,
      "max_score": 59.67122908962842,
      "measured_at": null,
      "min_score": 17.38109358780758,
      "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": 800,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.6737316040624,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 26.42557071449074,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 534,
      "capped_draws": 120,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.06200699999999999,
        "mean": 0.042994687499999996,
        "median": 0.0423105,
        "min": 0.0223935,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.34395749999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.20167797369913,
      "contributing_entrants": null,
      "distinct_rated_opponents": 248,
      "draws": 130,
      "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": "2026-08-05T05:02:41Z",
      "losses": 217,
      "max_score": 37.07858798158563,
      "measured_at": null,
      "min_score": 22.730135675874582,
      "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": 499,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.7939790261225,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 25.396482742730665,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 35,
      "wins": 152
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 656,
      "capped_draws": 232,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 30
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 30,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 25.618760741182353,
      "contributing_entrants": null,
      "distinct_rated_opponents": 303,
      "draws": 232,
      "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": "2026-08-05T05:16:56Z",
      "losses": 310,
      "max_score": 27.82104904701147,
      "measured_at": null,
      "min_score": 22.417196747929975,
      "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": 652,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.6116229817628,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": 2,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 19.154491325362542,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 110
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 472,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 236,
      "draws": 112,
      "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": "2026-07-31T03:34:49Z",
      "losses": 267,
      "max_score": 41.19784660229971,
      "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": 472,
      "rating_method": "sequential_elo",
      "raw_elo": 1228.2514306279427,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 17.319128239553702,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 2049.195935972635,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 97.55488190852645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 22,
      "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": "2026-08-05T05:08:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1787.0910986805159,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 72.251918530255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 284,
      "capped_draws": 123,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 138,
      "draws": 123,
      "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": "2026-08-05T05:16:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 283,
      "rating_method": "sequential_elo",
      "raw_elo": 1743.5487349270413,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 68.29057346028767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-07-31T02:50:24Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.9941068004882,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.377814269152495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-07-31T03:24:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.3217926636212,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.814684949492396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T03:05:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.0420650084584,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.78600839000461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-07-31T02:53:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.9048927563001,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.303844169868434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "capped_draws": 110,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 110,
      "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": "2026-08-05T05:09:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.0891855735679,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.11478815980904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-08-05T04:26:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 139,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.2246913986785,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.447789575371836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.2174621120816,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.2908922032663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 83,
      "draws": 123,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.567868491681,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.12110302067223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 23.59559994608984,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-07-31T02:07:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.707369380218,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.77193143521104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 234,
      "capped_draws": 106,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 106,
      "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": "2026-08-05T05:37:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.222833880484,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.76771663674732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.250945381480301,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 284,
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 138,
      "draws": 64,
      "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": 130,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.0320223634517,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.88673329517897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 160,
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 80,
      "draws": 115,
      "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": "2026-08-05T05:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.041221974691,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.199740947921946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 23.654864507219585,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 386,
      "capped_draws": 88,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 192,
      "draws": 88,
      "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": 163,
      "max_score": null,
      "measured_at": "2026-08-05T01:58:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 386,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.0186160606256,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.07384132839297,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9009167740720869,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 86,
      "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": "2026-08-05T05:02:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.9162067080504,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.2640459642207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T03:13:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.448626577189,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.22577138332814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 94,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 47,
      "draws": 57,
      "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": "2026-08-05T05:26:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.1741194955482,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.043380004909636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 27.57795513865966,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-04T22:07:16Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.4307170357656,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.791267003138834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-08-05T04:27:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.7795894298745,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.50826721476022,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T05:27:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.1194224909668,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Reasoning field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.478292990152276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 396,
      "capped_draws": 61,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 198,
      "draws": 61,
      "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": 178,
      "max_score": null,
      "measured_at": "2026-07-31T03:20:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.6405250902899,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.064171182767296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.259380609588918,
      "unilateral_faults": 0,
      "wins": 157
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 366,
      "capped_draws": 114,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 147,
      "draws": 114,
      "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": 139,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.404832296831,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.9946317420071,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.8116737375058,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.54208643626219,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 278,
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 133,
      "draws": 92,
      "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": 103,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:00Z",
      "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": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.3980802647104,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.772634831663424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 500,
      "capped_draws": 143,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 243,
      "draws": 143,
      "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": 216,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:00Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 494,
      "rating_method": "sequential_elo",
      "raw_elo": 1400.1087975800988,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.869164176499254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.2807380098319099,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 50,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.785287112545,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.546723164957854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 27.367480145108665,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 129,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.8251838934389,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.086613675695194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.10290096535146454,
      "unilateral_faults": 35,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-04T23:49:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.949051352309,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.520204387389295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 374,
      "capped_draws": 110,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 185,
      "draws": 110,
      "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": 172,
      "max_score": null,
      "measured_at": "2026-08-05T05:15:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 374,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.0336204181292,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.269988200342766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.1643552942737934,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.834157637065,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.947576637723415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.029700787957108,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.5548143433798,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.248133482989893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 33.16054548991772,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-05T01:59:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 121,
      "rating_method": "sequential_elo",
      "raw_elo": 1294.2112404069253,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.602289135184463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.5178730212592662,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 274,
      "capped_draws": 116,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 129,
      "draws": 116,
      "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": 128,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1269.590378771029,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.417196747929975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.6667408666858066,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 278,
      "capped_draws": 104,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 133,
      "draws": 104,
      "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": "2026-08-05T05:09:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 277,
      "rating_method": "sequential_elo",
      "raw_elo": 1223.4085617983565,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.986293369286603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-07-31T03:26:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1181.758735531149,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 13.34873652645807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 230,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 115,
      "draws": 96,
      "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": "2026-08-05T04:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1673.5108063757525,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 63.32315344250023,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.6751283820590555,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "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": 74,
      "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": "2026-08-05T03:05:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.202321522418,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.15647522370581,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-05T01:51:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.7410235438656,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.416670221124697,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 106,
      "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": "2026-08-05T04:33:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.7314778179798,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.58345519069338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 96,
      "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": "2026-08-04T21:44:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.4800705170592,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.69560465698689,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-03T08:48:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.230475769869,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.43537970074668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.926723016124,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.09530085961754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 92,
      "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": "2026-08-04T23:05:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.9195447594993,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.30438447793437,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 80,
      "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": "2026-08-04T23:04:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.2207038900344,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.482461561801962,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 100,
      "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": "2026-08-03T15:08:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.7598583404967,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.448726851866137,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 306,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 152,
      "draws": 285,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-04T22:55:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.4883162878389,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.737279542205624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.521109022046928,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 118,
      "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": "2026-08-05T04:33:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.7815159368622,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.571994896490278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 106,
      "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": "2026-08-05T03:06:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.6685144794933,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.375595771095142,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 197,
      "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": "2026-08-05T00:35:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.3978500172125,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.33030113424673,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.321602512009086,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 99,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.1067750294355,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.259905179055554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 114,
      "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": "2026-08-05T04:26:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.8238680319553,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.765351621675194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "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": 91,
      "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": "2026-07-31T03:31:12Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.363551009849,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.22265746079894,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 75,
      "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": "2026-07-31T03:32:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.4985994938952,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.047433762857775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 102,
      "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": "2026-08-05T04:33:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.2460261587667,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.60034070265804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 434,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 216,
      "draws": 398,
      "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": "2026-08-05T04:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 434,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.154753586598,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.59118479048314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.081522477821102,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 142,
      "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": "2026-08-05T04:27:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.0305995079593,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.08311558138147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-05T02:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.4026985942367,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.371420182291875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 256,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 128,
      "draws": 231,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.6639372088994,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.84653261324441,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.06462264614784,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 65,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:27:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.4735135903006,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.703162245681458,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 31.92684787488294,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 93,
      "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": "2026-08-05T04:33:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.554229345278,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.49414607975783,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 81,
      "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": "2026-08-05T02:59:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.39352975317,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.488893388132354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 92,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T04:32:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.370338353978,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.38109358780758,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "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": 144,
      "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": "2026-08-05T04:33:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.2406346349167,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.907630545609305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 36.3536321005172,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 52,
      "draws": 124,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T04:27:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.5326509606543,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.238936021776848,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 48.18433039621293,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "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": 136,
      "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": "2026-08-05T04:33:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.2464671154166,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 15.356957668247802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 39.307153450636115,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "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": 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": 8,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:22Z",
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.0350810658178,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 13.313054666786927,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T03:55:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.1421724289517,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.01848820960669,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 105,
      "draws": 39,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.538456140085,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.60139245654345,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.828889084636114,
      "unilateral_faults": 0,
      "wins": 107
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 106,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 53,
      "draws": 34,
      "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": "2026-08-04T21:24:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.589788520244,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.1413174012522,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 37.60341101879811,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 70,
      "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": "2026-08-05T02:50:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.2621082602757,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.85859288843461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 42,
      "draws": 60,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.2009489848747,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.18173729841307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 31.670087811963565,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.6690644495093,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.65724563741933,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 28.08463570631327,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 41,
      "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": "2026-08-05T05:17:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.1113435198147,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.47234326149914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.5513087187508,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.96266756353682,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 96,
      "draws": 94,
      "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": "2026-08-05T05:23:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.0195089700449,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.88653195721722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 55,
      "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": "2026-08-05T04:02:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.0791075326886,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.825908860305795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 42,
      "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": "2026-08-03T13:39:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.6386415291488,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.7417856969161,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 302,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 151,
      "draws": 172,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-08-05T04:03:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.4152606481027,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.007466418277744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.884068654918515,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T01:37:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.5833143372236,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.87270762029662,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 36,
      "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": "2026-08-05T03:55:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.4575917303791,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.871448824939826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 47,
      "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": "2026-08-05T05:24:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.2219053386525,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.47520283021661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 94,
      "draws": 75,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.9147812034898,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.908955370742355,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.311964357860807,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 51,
      "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": "2026-08-05T05:17:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.459954262159,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.324362595440974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 34,
      "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": "2026-08-05T02:49:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.96396152062,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.56114839964518,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 180,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 90,
      "draws": 83,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "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": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.0805512513246,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.32865162817713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.817010378902888,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "2026-08-05T05:23:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.1293236265938,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.94223147070685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 204,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 102,
      "draws": 87,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-07-31T03:07:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.6337719916312,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.95596680854231,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.493622478518038,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 282,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 137,
      "draws": 101,
      "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": 109,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:13Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.7658989510273,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.687958478700622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.692178568782805,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 69,
      "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": "2026-08-03T11:47:32Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.1509269893077,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.410317232417285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "draws": 83,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.7986598115863,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.99213047697091,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.251875136730032,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-07-31T02:59:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.2542607455403,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.603816053425483,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 86,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 53,
      "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": "2026-08-03T15:07:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.1018350385903,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.18896644366903,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 252,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 102,
      "draws": 106,
      "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": 97,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.5273535246738,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.15995528948202,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.6219524331384951,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 28,
      "draws": 41,
      "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": "2026-08-04T20:26:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.2594736718875,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.457791809431576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 43.9177814856242,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 54,
      "draws": 69,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-08-05T04:45:00Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.2109374982958,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.850957987441,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 31.655454738281755,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-04T22:38:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.8681392042768,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.2055412078098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 67,
      "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": "2026-08-05T05:32:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.8397934807497,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.45429450824968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 250,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 125,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:34Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.5843980718105,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.570204853782045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.7945925104007445,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 65,
      "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": "2026-07-31T02:32:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.8964765379387,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.553899944193034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": "2026-08-05T02:20:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.471964521424,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.626895289462276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 86,
      "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": "2026-08-05T05:33:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.5967389400641,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.93334802211057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 60,
      "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": "2026-08-05T03:48:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.5637786917036,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.4004936024422,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 98,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 49,
      "draws": 115,
      "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": "2026-08-05T06:56:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.5867928352518,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.549162054857096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 31.961000041312673,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 130,
      "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": "2026-08-05T05:33:30Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.684673413206,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.91354977203183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 64,
      "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": "2026-07-31T02:30:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.923140293816,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.378827209357606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-08-04T23:35:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.6015655750139,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.225424673213766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.9358300464557,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.207725737710934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 350,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 175,
      "draws": 263,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-07-31T02:43:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.0847759258468,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.02813630675977,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.456975972465711,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 84,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.788961263713,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.724504900603456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 27,
      "draws": 85,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.5332726354854,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.318855181547832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 44.97152085681538,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 84,
      "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": "2026-08-05T01:02:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.5395240183984,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.65944702485429,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 79,
      "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": "2026-08-05T03:47:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.0901092415422,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.334173890509387,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 208,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 102,
      "draws": 153,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T02:20:00Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.9735934356604,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.59744302717278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 182,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 91,
      "draws": 148,
      "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": "2026-07-31T02:31:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.5180903312562,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.575209497586215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.380913286308589,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 81,
      "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": "2026-08-04T23:28:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.7609209020502,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.455964717492304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 101,
      "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": "2026-08-05T02:13:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.005582006335,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.076279916551638,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 218,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 107,
      "draws": 153,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-08-05T05:32:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.2060981772852,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.004687671221845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.960122029721176,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 20,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.8549762856173,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.77246145445514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 36.393187298490844,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.7100792380625,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.412668235568347,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 81,
      "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": "2026-08-05T05:32:54Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.8750459371463,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.006731116118797,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 31,
      "draws": 132,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.4924064050508,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.82534266256079,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 36.30505935463012,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 342,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 169,
      "draws": 256,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:34Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.132843310276,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.9977782784657,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.8856705632567614,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 306,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 152,
      "draws": 247,
      "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": "2026-08-05T05:33:30Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.841790346759,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.412909336833845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.575689184935122,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T06:57:15Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.6747251558618,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 9.425383107713568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 44.09288922855442,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 288,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 144,
      "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": "2026-08-05T04:56:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 2016.6529826130795,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 87.54961526135239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 262
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-03T09:10:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1852.4714723440495,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 73.59018908373541,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "2026-08-05T02:32:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1654.2910020114755,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.22626896121154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 54,
      "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": "2026-08-05T05:06:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1639.773680061784,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.986630660102286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.36946558518069,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "2026-07-31T02:29:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1611.682762884176,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.4061534092432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-08-05T05:13:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.2941355766166,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.07100335059694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 24.31577533888108,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 236,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 118,
      "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": 88,
      "max_score": null,
      "measured_at": "2026-08-05T00:20:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.3571049572838,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.809153048377176,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.089780903323941,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T00:20:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.5212453673003,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.63127668910358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:40:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.7302568220246,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.38205655158486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:32:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.7324094191993,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.49884905114305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T01:37:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.5681458624933,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.34237964243975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "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": 85,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.687707880838,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.911341645144915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.61525389910498,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:40:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.2916673268228,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.955454000683424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-03T11:29:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.8798297824787,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.653927467729666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-03T11:38:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.8535519192562,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.95654254826272,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 410,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 205,
      "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": 206,
      "max_score": null,
      "measured_at": "2026-07-31T03:35:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 410,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.4230061325848,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.31485423521351,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.423535000954365,
      "unilateral_faults": 0,
      "wins": 204
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "2026-08-03T11:37:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2207722244411,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.296018158068726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 334,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 167,
      "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": 176,
      "max_score": null,
      "measured_at": "2026-08-03T14:20:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.9556199173985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.583428548446186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.4266622086615564,
      "unilateral_faults": 0,
      "wins": 158
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:56:17Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.9852834380013,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.002182892666326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-08-03T12:50:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.595814890767,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.34046965332213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-03T14:20:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.4191254057696,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.26747573047881,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 376,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 188,
      "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": 214,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 376,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.534006668353,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.982306358442266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.0126757293056905,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "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": 20,
      "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": "2026-08-05T05:05:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.2948562490126,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.188022973615546,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 36.393187298490844,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 364,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 182,
      "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": 223,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:55Z",
      "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": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.745838091093,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.727067905022835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.4690985922539064,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 254,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 155,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:55Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.3191922229553,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.593166509925418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.48567977499789805,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "2026-08-03T11:38:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1337.1021659225844,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.911374561641104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:56:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.945520868201,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.06235888002087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1291.0038555913918,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.543257483194672,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 24.96298192699785,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 360,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 180,
      "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": 262,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 360,
      "rating_method": "sequential_elo",
      "raw_elo": 1238.0288756535647,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.69114574283472,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7169737855478928,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 128,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1245.754396970667,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.109036910675474,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 35.2114810203569,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-08-05T02:32:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1201.3664980516578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.625108861534393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "2026-08-05T04:55:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1142.4053752159446,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 14.75877111394388,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 232,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 114,
      "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": 172,
      "max_score": null,
      "measured_at": "2026-08-03T22:34:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1131.6573902393625,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 13.789037064172394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.880529885641141,
      "unilateral_faults": 4,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1111.844236303335,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 12.001624306152966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-03T23:25:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 966.111945528687,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 2,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 15,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1968.7663861920653,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 96.50163167645941,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-03T09:48:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1695.989456164501,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 70.28014429931316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-08-03T11:04:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1663.2988732348192,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 67.31147896345796,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 60,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:36Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.6643540912712,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 62.82646209967631,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.571060443119833,
      "unilateral_faults": 0,
      "wins": 128
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.5694499676742,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.42525560215735,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 36.926617622282734,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-03T13:58:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1566.5712031640337,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.99889288812461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 366,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 181,
      "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": 157,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.4143973553253,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.65051046409322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.360347800585077,
      "unilateral_faults": 0,
      "wins": 205
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-03T13:58:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.1182735858504,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.63398289929676,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.5251926323524,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.50967288140359,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 31.621021663051927,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T01:59:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.8036267291184,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.03010894281152,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 60,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:18Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.361759571965,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.32856442995505,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.14703191068986,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 326,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 161,
      "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": 168,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.9037775432546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.233162638067576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.098238467332041,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 250,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 123,
      "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": 123,
      "max_score": null,
      "measured_at": "2026-08-05T04:32:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.3729776380346,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.14506340139004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.042462425705284,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.3666186655798,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.345931211891994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 364,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 182,
      "draws": 25,
      "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": 206,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.7359612918535,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.139430458543245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.390159544298225,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-08-03T13:58:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.6560155217642,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.187078959151634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-03T09:47:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.139471593564,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.005316505702595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.605642525274,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.569177511800305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.755845925186044,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-07-31T02:02:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.5270623462427,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.19784660229971,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.7066706089265,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.82667813491906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T05:20:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.4703196886467,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.608044412593436,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.09174363298229,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 358,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 174,
      "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": 184,
      "max_score": null,
      "measured_at": "2026-08-05T01:52:26Z",
      "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": 358,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.455342849291,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.586565302093824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.8559527250035135,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-05T00:42:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.9510085269612,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.046844177408595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-05T00:42:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.0460288080308,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.07858798158563,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1326.421769500473,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.572024225518824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "draws": 21,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1333.2717926998414,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.7490542863941,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.84785372359809,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 117,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-08-05T03:19:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 117,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.1028923436827,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.075295219829112,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.2787308949161655,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-07-31T02:45:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1264.9730824819735,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.146749768317104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": "2026-08-05T03:20:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1252.718659169334,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.28420303224434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "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": 62,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.6597352187855,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.704436166861854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1237.0938999004793,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.92797843552678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 224,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "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": 154,
      "max_score": null,
      "measured_at": "2026-08-05T03:19:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1234.071746624579,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.575835233971056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.335874651846873,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 292,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 115,
      "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": 220,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1130.0626959606705,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.149445622957767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": 96,
      "max_score": null,
      "measured_at": "2026-08-05T01:51:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1011.1739414944491,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 5.362618665013622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "2026-08-03T14:13:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1871.6449499623504,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 79.53649997231051,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-03T08:56:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1748.906549027976,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 68.55479086064098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "2026-08-03T14:14:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1648.2632211454757,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 59.67122908962842,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-08-05T00:35:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.7821015362729,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 59.006818274433016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:30:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.2594219728185,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.248540146399066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 40.79847712741414,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 52,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 26,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-08-05T04:30:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.364249622662,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.213321937541714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 40.499923295317174,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "2026-08-05T01:45:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1587.987129981108,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.34437188783892,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 296,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 148,
      "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": 146,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.0224149727546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.257859859863686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.345220975952071,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "2026-08-03T14:14:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.0312688394026,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.14430473568327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "2026-08-03T14:04:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.68608538996,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.58029710675838,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.5214241665924,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 52.11814186315531,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 61,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.7689040110965,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.56860730824784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 38.878822395858876,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 252,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "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": 134,
      "max_score": null,
      "measured_at": "2026-08-04T01:46:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.7113363007984,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.5535341301958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.5190135939585359,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T01:37:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.9851381905353,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.33771077624585,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:31:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.7500742829843,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.42172085598957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 31.621021663051927,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.1898440671557,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.15956696391413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-08-03T12:28:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.7320098290559,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.598572223588526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 252,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "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": "2026-08-05T05:24:25Z",
      "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": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.751951341211,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.11567729374995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.8522727272727293,
      "unilateral_faults": 0,
      "wins": 128
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-08-03T12:43:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.0972054047072,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.26086585514032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 113,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:47Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.6505860863158,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.44754596890132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 25.906255061212047,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T06:57:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.2617719734535,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.895583637620526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.438955443770794,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-08-05T04:09:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.4735570462385,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.34465187857206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.2913737732042,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.285058901033004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 326,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 161,
      "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": 188,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:25Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.7381559646585,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.17318662888423,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.000874675844361,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 220,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 125,
      "max_score": null,
      "measured_at": "2026-08-03T22:56:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.401767487915,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.05907819296716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.936433935731518,
      "unilateral_faults": 2,
      "wins": 93
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 225,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 112,
      "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": 138,
      "max_score": null,
      "measured_at": "2026-08-03T22:28:24Z",
      "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": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1287.3461805364666,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.498910992576068,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.3747745509860616,
      "unilateral_faults": 1,
      "wins": 86
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 236,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 156,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:56Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.7241426466258,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.618036428605613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.4952944368626584,
      "unilateral_faults": 4,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": "2026-08-03T21:49:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1273.2695604121793,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.19428053874851,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 2,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1262.0756595302967,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.230925188782717,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-08-05T04:31:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1256.5767702858623,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.83779534181248,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.51693271964983,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 327,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 157,
      "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": 244,
      "max_score": null,
      "measured_at": "2026-08-04T01:46:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 322,
      "rating_method": "sequential_elo",
      "raw_elo": 1167.1939517552057,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.762689788970278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.29384956406377,
      "unilateral_faults": 5,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 107,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-08-03T23:25:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1140.8549909594703,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 14.402666706405672,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 1,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-07-31T03:28:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1123.552445089051,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 12.693314222369741,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": "2026-08-04T01:12:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1097.921478157074,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 10.523618948427423,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 2,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 980.6285194650904,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-08-03T04:47:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1782.5639360440102,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 68.98590691472927,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": 30,
      "max_score": null,
      "measured_at": "2026-08-03T01:17:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1746.3197512997453,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 64.91944958274557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 232,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 8,
      "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": 62,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1748.4616627962346,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 64.90150228152228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.241307227332022,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 70,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1726.5150017837482,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 62.96894118841835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 138,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 69,
      "draws": 3,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-04T23:19:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1742.9337561743264,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 61.644694598987854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.93195887871912,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 138,
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 69,
      "draws": 35,
      "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": "2026-08-05T04:53:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1671.3613009319051,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.79745130191461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.195323654719896,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 302,
      "capped_draws": 90,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 151,
      "draws": 90,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-07-31T20:23:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.288920722461,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.07415527631838,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.859591937440758,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 106,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "draws": 106,
      "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": "2026-08-03T03:56:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.3284416661595,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.39648748043947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 17,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-08-02T23:32:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.5659164262063,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.56442313471822,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-08-02T23:32:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.6098803293485,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.69816826394159,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 520,
      "capped_draws": 331,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 255,
      "draws": 331,
      "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": 105,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 520,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.8757642909575,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.38644028078468,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.42613636363636465,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "capped_draws": 101,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 101,
      "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": "2026-08-05T01:22:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.5223595698037,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.760804539439587,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 109,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T03:32:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.7781869391822,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.734330041940417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 99,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 99,
      "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": "2026-08-05T05:41:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.4172481872668,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.495214909397852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 278,
      "capped_draws": 244,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 133,
      "draws": 244,
      "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": "2026-08-05T05:41:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.369819758583,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.390406342527847,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "capped_draws": 91,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 91,
      "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": "2026-08-05T05:41:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.374254888266,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.291653340113125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 91,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 91,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-04T07:10:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.3097970155627,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.273880023544745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 2,
      "wins": 6
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 400,
      "capped_draws": 290,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 197,
      "draws": 290,
      "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": 83,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:30Z",
      "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": 398,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.178803898413,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.926757621782304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.8250054507008079,
      "unilateral_faults": 2,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "capped_draws": 116,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 116,
      "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": "2026-08-05T03:33:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.5203475276332,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.82104904701147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "capped_draws": 114,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 114,
      "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": "2026-08-04T22:07:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.331625152364,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.747877916943,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 96,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 96,
      "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": "2026-07-31T02:32:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.8696093056199,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.4031104365134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 378,
      "capped_draws": 329,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 148,
      "draws": 329,
      "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": "2026-08-05T05:41:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 374,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.8180210731284,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.381746596189068,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "capped_draws": 105,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 105,
      "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": "2026-08-05T05:41:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.2782648293512,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.37599577178315,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "capped_draws": 112,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.3766557322458,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.19008980579632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 278,
      "capped_draws": 240,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 133,
      "draws": 240,
      "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": "2026-08-05T05:40:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 277,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.6618782515638,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.059297656013577,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "capped_draws": 90,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 50,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:49Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.4319843854755,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.88284327640182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 27.748044770341348,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 92,
      "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": "2026-08-05T05:33:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.1694751108657,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.74278235761671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 106,
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 53,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.3374186238389,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.53818816474888,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 27.689018606881785,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 402,
      "capped_draws": 311,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 198,
      "draws": 311,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 402,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.5660382499407,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.52517243388469,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.44449391112387104,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "capped_draws": 129,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 129,
      "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": "2026-08-05T05:41:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.731723298986,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.798477633166108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.9115222168389,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.78316364121671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 46.55344771392958,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 70,
      "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": "2026-08-05T05:41:08Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.438879424766,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.48313253075837,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 31.77863397214846,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T05:41:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.6511322068186,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.170311606444997,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 46.55344771392958,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "capped_draws": 110,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 70,
      "draws": 110,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T04:49:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.202537480436,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.730135675874582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 238,
      "capped_draws": 169,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 119,
      "draws": 169,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.3990143028504,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.075114883794193,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.8947351529780132,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 914,
      "capped_draws": 1,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 1.91725,
        "mean": 1.58262125,
        "median": 1.5854,
        "min": 1.05322,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 12.660969999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 83.35739367463012,
      "contributing_entrants": null,
      "distinct_rated_opponents": 417,
      "draws": 126,
      "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": "2026-08-05T04:44:21Z",
      "losses": 143,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 68.08895739222693,
      "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": 914,
      "rating_method": "sequential_elo",
      "raw_elo": 1861.9215228524424,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 83.35739367463012,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 645
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 1086,
      "capped_draws": 2,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 3,
        "max": 2.09943,
        "mean": 1.379653125,
        "median": 1.3205149999999999,
        "min": 0.8875599999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 22.07445
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 81.79307965612657,
      "contributing_entrants": null,
      "distinct_rated_opponents": 487,
      "draws": 75,
      "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": "2026-08-05T04:52:03Z",
      "losses": 170,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 61.3843149316053,
      "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": 1086,
      "rating_method": "sequential_elo",
      "raw_elo": 1864.6719075807764,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 77.65553263999308,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 841
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 882,
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 3.2933475,
        "mean": 2.642580625,
        "median": 2.681945,
        "min": 1.562975,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.140645
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 72.12620352118518,
      "contributing_entrants": null,
      "distinct_rated_opponents": 410,
      "draws": 172,
      "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": "2026-08-05T04:44:25Z",
      "losses": 143,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 32.829666021771125,
      "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": 880,
      "rating_method": "sequential_elo",
      "raw_elo": 1811.9321887861538,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 72.12620352118518,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 565
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 902,
      "capped_draws": 21,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 12.915325,
        "mean": 10.059243749999998,
        "median": 10.0094025,
        "min": 8.401555,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 80.47395
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 66.33428289138148,
      "contributing_entrants": null,
      "distinct_rated_opponents": 415,
      "draws": 101,
      "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": "2026-08-05T04:22:45Z",
      "losses": 247,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 19.935559087203618,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 902,
      "rating_method": "sequential_elo",
      "raw_elo": 1703.0249169525546,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 66.33428289138148,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 554
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 864,
      "capped_draws": 20,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 1.38945,
        "mean": 0.93123625,
        "median": 0.95991,
        "min": 0.36561,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 7.449890000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 68.15597422847155,
      "contributing_entrants": null,
      "distinct_rated_opponents": 398,
      "draws": 109,
      "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": "2026-08-05T04:43:45Z",
      "losses": 223,
      "max_score": 86.15355149666183,
      "measured_at": null,
      "min_score": 49.197008068659926,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 864,
      "rating_method": "sequential_elo",
      "raw_elo": 1724.589320143444,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 65.9182916044786,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 532
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 793,
      "capped_draws": 60,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 4.4173,
        "mean": 2.7356843750000004,
        "median": 2.536595,
        "min": 2.045485,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.885475
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 66.32419996398228,
      "contributing_entrants": null,
      "distinct_rated_opponents": 377,
      "draws": 153,
      "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": "2026-08-05T04:44:25Z",
      "losses": 171,
      "max_score": 90.99516388242985,
      "measured_at": null,
      "min_score": 12.006801731616441,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 792,
      "rating_method": "sequential_elo",
      "raw_elo": 1769.9698024775964,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 64.14665776772328,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 468
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 906,
      "capped_draws": 57,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 12.137519999999999,
        "mean": 8.1660015625,
        "median": 8.18098,
        "min": 4.7142525,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 65.3280125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 55.34391807732854,
      "contributing_entrants": null,
      "distinct_rated_opponents": 424,
      "draws": 187,
      "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": "2026-08-05T04:35:30Z",
      "losses": 299,
      "max_score": 74.75879788264669,
      "measured_at": null,
      "min_score": 40.24489520124794,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 906,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.680291544217,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 55.34391807732854,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 420
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 904,
      "capped_draws": 14,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 4.987857,
        "mean": 3.1645696249999995,
        "median": 3.0710854999999997,
        "min": 1.985613,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 28.806540999999996
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 51.61421606005783,
      "contributing_entrants": null,
      "distinct_rated_opponents": 433,
      "draws": 202,
      "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": "2026-08-05T04:35:08Z",
      "losses": 292,
      "max_score": 79.30739463261588,
      "measured_at": null,
      "min_score": 22.061882688196544,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 904,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.9955654657704,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 50.11655440056413,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 410
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": 1194,
      "capped_draws": 26,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 50
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.19006573333333335,
        "mean": 0.11809463333333332,
        "median": 0.09664113333333335,
        "min": 0.06671613333333333,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 50
        },
        "recorded_attempt_count": 50,
        "run_count": 24,
        "total": 2.8342712000000003
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 48.905709680771956,
      "contributing_entrants": null,
      "distinct_rated_opponents": 597,
      "draws": 325,
      "entry_count": 37,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:57:05Z",
      "losses": 579,
      "max_score": 68.96755045489611,
      "measured_at": null,
      "min_score": 18.785677670777737,
      "model_code_failure_rate": 0.08333333333333333,
      "model_code_failures": 2,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 0.9166666666666666,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1194,
      "rating_method": "sequential_elo",
      "raw_elo": 1610.1661170861369,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.08333333333333333,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 47.853358704885466,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1022
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1450,
      "capped_draws": 94,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 2,
          "local_standard_estimate": 18
        },
        "evidence_basis": "Mixed: Recorded attempt + Standard list-price estimate",
        "max": 1.5164726249999998,
        "mean": 1.0788743062500001,
        "median": 0.9700117500000001,
        "min": 0.8356068750000001,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-07-30": 18
        },
        "recorded_attempt_count": 2,
        "run_count": 14,
        "token_priced_attempt_count": 18,
        "total": 15.220633649999998
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 46.73048991131135,
      "contributing_entrants": null,
      "distinct_rated_opponents": 695,
      "draws": 362,
      "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": "2026-08-05T04:52:03Z",
      "losses": 511,
      "max_score": 72.91920929796846,
      "measured_at": null,
      "min_score": 18.231928182356505,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1450,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.5490296647502,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 2,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 46.73048991131135,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 577
    },
    {
      "admitted_plugins": 20,
      "attempted_matches": 810,
      "capped_draws": 29,
      "codegen_cost_usd": {
        "admitted_cell_count": 20,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 65
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 1.1177706,
        "mean": 0.8961934,
        "median": 0.9197228499999999,
        "min": 0.6673354000000001,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 65
        },
        "recorded_attempt_count": 65,
        "run_count": 26,
        "total": 23.267240399999995
      },
      "codegen_evaluated_cells": 25,
      "conditional_success_score": 48.43186177867785,
      "contributing_entrants": null,
      "distinct_rated_opponents": 405,
      "draws": 264,
      "entry_count": 25,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 16,
      "first_pass_rate": 0.64,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_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": "2026-08-05T06:57:15Z",
      "losses": 249,
      "max_score": 76.9153537911332,
      "measured_at": null,
      "min_score": 20.09827284833638,
      "model_code_failure_rate": 0.2,
      "model_code_failures": 5,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 0.8,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 810,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.0233363316154,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 4,
      "repaired_rate": 0.16,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 45.804026885586204,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 491
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 641,
      "capped_draws": 69,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.531673125,
        "mean": 0.47737264687500003,
        "median": 0.48302475,
        "min": 0.3855675,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 7.6379623500000005
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 48.607615644623934,
      "contributing_entrants": null,
      "distinct_rated_opponents": 321,
      "draws": 182,
      "entry_count": 24,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-07"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:56:18Z",
      "losses": 321,
      "max_score": 72.5401989690437,
      "measured_at": null,
      "min_score": 35.01219161214689,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 641,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.3973922391638,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 45.23448330825427,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 532
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 1120,
      "capped_draws": 107,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.4567,
        "mean": 0.3802064166666667,
        "median": 0.3908776666666667,
        "min": 0.234622,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 10,
        "token_priced_attempt_count": 11,
        "total": 3.8844619999999996
      },
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 44.378482409071644,
      "contributing_entrants": null,
      "distinct_rated_opponents": 530,
      "draws": 350,
      "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": "2026-08-05T04:45:00Z",
      "losses": 411,
      "max_score": 62.31323923781224,
      "measured_at": null,
      "min_score": 29.014574794367363,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1120,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.644384166015,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 44.378482409071644,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 359
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 1728,
      "capped_draws": 252,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 2,
          "local_standard_estimate": 29
        },
        "evidence_basis": "Mixed: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.38568888333333334,
        "mean": 0.288318396875,
        "median": 0.28604548333333335,
        "min": 0.22385259999999998,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-07-30": 29
        },
        "recorded_attempt_count": 2,
        "run_count": 20,
        "token_priced_attempt_count": 29,
        "total": 5.92105485
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": 42.5715192844583,
      "contributing_entrants": null,
      "distinct_rated_opponents": 830,
      "draws": 510,
      "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": "2026-08-05T04:43:45Z",
      "losses": 649,
      "max_score": 88.3001049099167,
      "measured_at": null,
      "min_score": 18.002828160874977,
      "model_code_failure_rate": 0.11764705882352941,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1727,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.9596145279502,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 5,
      "repaired_rate": 0.29411764705882354,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 41.26004847678181,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 568
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 748,
      "capped_draws": 113,
      "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": 43.9705511062461,
      "contributing_entrants": null,
      "distinct_rated_opponents": 361,
      "draws": 177,
      "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": "2026-08-05T05:11:41Z",
      "losses": 304,
      "max_score": 76.14344213568862,
      "measured_at": null,
      "min_score": 25.042469828678968,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": 0.75,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 748,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.6070630471286,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 40.919208516869816,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 267
    },
    {
      "admitted_plugins": 20,
      "attempted_matches": 2195,
      "capped_draws": 277,
      "codegen_cost_usd": {
        "admitted_cell_count": 20,
        "cell_count": 8,
        "cost_basis_counts": {
          "exact_cumulative_delta": 1,
          "provider_reported": 64
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.25823185295,
        "mean": 0.20846239076375003,
        "median": 0.20662718916666667,
        "min": 0.13654539825,
        "recorded_attempt_count": 65,
        "run_count": 29,
        "total": 5.97530434986
      },
      "codegen_evaluated_cells": 27,
      "conditional_success_score": 42.31385173430746,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1053,
      "draws": 713,
      "entry_count": 20,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.1111111111111111,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_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": "2026-08-05T05:05:01Z",
      "losses": 790,
      "max_score": 76.82222311841032,
      "measured_at": null,
      "min_score": 20.17228110668475,
      "model_code_failure_rate": 0.25925925925925924,
      "model_code_failures": 7,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 0.7407407407407407,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2187,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.2952285458111,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 17,
      "repaired_rate": 0.6296296296296297,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 39.2553738606206,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 8,
      "wins": 684
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 489,
      "capped_draws": 45,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.45464499999999997,
        "mean": 0.28201406249999994,
        "median": 0.2695775,
        "min": 0.17401125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 2.2561125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.58016390752029,
      "contributing_entrants": null,
      "distinct_rated_opponents": 244,
      "draws": 303,
      "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": "2026-08-05T05:05:23Z",
      "losses": 324,
      "max_score": 66.50580979104048,
      "measured_at": null,
      "min_score": 16.793318043756123,
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 488,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.6253461342465,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.58016390752029,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 309
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 370,
      "capped_draws": 36,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.6921525,
        "mean": 0.48907706250000005,
        "median": 0.483741,
        "min": 0.401826,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 3.9126164999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.41206956369944,
      "contributing_entrants": null,
      "distinct_rated_opponents": 185,
      "draws": 182,
      "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": "2026-08-05T05:04:52Z",
      "losses": 250,
      "max_score": 77.86243893295662,
      "measured_at": null,
      "min_score": 12.88406623711618,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 370,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.7605198475023,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.538273161452864,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 234
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 474,
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.73533,
        "mean": 0.5886581249999999,
        "median": 0.58241,
        "min": 0.410635,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.709265
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.43255487282136,
      "contributing_entrants": null,
      "distinct_rated_opponents": 237,
      "draws": 425,
      "entry_count": 16,
      "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": "2026-08-05T05:28:52Z",
      "losses": 544,
      "max_score": 54.40171912715226,
      "measured_at": null,
      "min_score": 17.12149396001877,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 474,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.6964641199188,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.43255487282136,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 483
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 474,
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.73533,
        "mean": 0.5886581249999999,
        "median": 0.58241,
        "min": 0.410635,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.709265
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.43255487282136,
      "contributing_entrants": null,
      "distinct_rated_opponents": 237,
      "draws": 425,
      "entry_count": 7,
      "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": "2026-07-31T20:22:43Z",
      "losses": 544,
      "max_score": 54.40171912715226,
      "measured_at": null,
      "min_score": 17.12149396001877,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 474,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.0438465023874,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 38.43255487282136,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 483
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 1072,
      "capped_draws": 84,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 32,
          "local_standard_estimate": 8
        },
        "evidence_basis": "Mixed: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 13,
        "max": 0.1097735,
        "mean": 0.091486,
        "median": 0.08840574999999999,
        "min": 0.07737849999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 40
        },
        "recorded_attempt_count": 32,
        "run_count": 32,
        "token_priced_attempt_count": 8,
        "total": 2.9275519999999995
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 40.42513666720264,
      "contributing_entrants": null,
      "distinct_rated_opponents": 534,
      "draws": 156,
      "entry_count": 38,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 19,
      "first_pass_rate": 0.59375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:56:55Z",
      "losses": 751,
      "max_score": 47.24502914491117,
      "measured_at": null,
      "min_score": 32.4038428924734,
      "model_code_failure_rate": 0.40625,
      "model_code_failures": 13,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.59375,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1068,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.9077340839624,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 35.48562040144815,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 714
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 1294,
      "capped_draws": 146,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.017371818,
        "mean": 0.00989701923,
        "median": 0.010218342,
        "min": 0.003562685,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 0.15835230767999997
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": 34.783090077371796,
      "contributing_entrants": null,
      "distinct_rated_opponents": 628,
      "draws": 314,
      "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": "2026-08-05T04:43:54Z",
      "losses": 598,
      "max_score": 54.873388733034076,
      "measured_at": null,
      "min_score": 21.713702201359574,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1294,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.5820692435125,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 6,
      "repaired_rate": 0.4,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 32.18796481877993,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 382
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 592,
      "capped_draws": 48,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 50
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0719635,
        "mean": 0.060768406250000004,
        "median": 0.0604727,
        "min": 0.05086675,
        "recorded_attempt_count": 50,
        "run_count": 16,
        "total": 0.9722945000000002
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 30.677141499448677,
      "contributing_entrants": null,
      "distinct_rated_opponents": 294,
      "draws": 250,
      "entry_count": 26,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.8125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:56:50Z",
      "losses": 433,
      "max_score": 44.976480556909316,
      "measured_at": null,
      "min_score": 18.1638721019117,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 588,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.6502948560828,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 29.66995603604416,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 283
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 442,
      "capped_draws": 20,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.007539277999999999,
        "mean": 0.0032457859375,
        "median": 0.0019568429999999998,
        "min": 0.001266762,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 0.031586439
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 30.2637506304396,
      "contributing_entrants": null,
      "distinct_rated_opponents": 220,
      "draws": 207,
      "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": "2026-08-05T05:11:51Z",
      "losses": 373,
      "max_score": 53.57176981147765,
      "measured_at": null,
      "min_score": 6.649465460691646,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 440,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.2072714576009,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 28.420821854316237,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 246
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 320,
      "capped_draws": 38,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.01660212,
        "mean": 0.008820586750000001,
        "median": 0.007023681,
        "min": 0.00271606,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.07056469400000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.34390555147243,
      "contributing_entrants": null,
      "distinct_rated_opponents": 160,
      "draws": 218,
      "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": "2026-08-05T05:11:31Z",
      "losses": 194,
      "max_score": 64.6891432709365,
      "measured_at": null,
      "min_score": 10.34354662706081,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.926620752997,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 27.869110936194055,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 341,
      "capped_draws": 44,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.11219570000000001,
        "mean": 0.0607572625,
        "median": 0.060057275,
        "min": 0.02174195,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.4860581
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.683163448529363,
      "contributing_entrants": null,
      "distinct_rated_opponents": 171,
      "draws": 101,
      "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": "2026-08-05T03:50:20Z",
      "losses": 347,
      "max_score": 40.06000231216052,
      "measured_at": null,
      "min_score": 13.030258973366303,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 341,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.6834766789484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 25.503339487650393,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 181
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 424,
      "capped_draws": 57,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.302804525,
        "mean": 0.259828169375,
        "median": 0.2529231275,
        "min": 0.22308452,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 4.15725071
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 26.89883327152712,
      "contributing_entrants": null,
      "distinct_rated_opponents": 210,
      "draws": 214,
      "entry_count": 18,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:37:42Z",
      "losses": 352,
      "max_score": 50.38530962978662,
      "measured_at": null,
      "min_score": 14.327060935420919,
      "model_code_failure_rate": 0.4375,
      "model_code_failures": 7,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.5625,
      "provider": "Other",
      "provider_key": "other",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 420,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.0307866527764,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 23.295072945304565,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 140
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 575,
      "capped_draws": 81,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.0456916,
        "mean": 0.031545040625,
        "median": 0.035551075,
        "min": 0.01864685,
        "recorded_attempt_count": 35,
        "run_count": 16,
        "total": 0.50472065
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 26.51417335977282,
      "contributing_entrants": null,
      "distinct_rated_opponents": 288,
      "draws": 441,
      "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": "2026-08-05T04:29:54Z",
      "losses": 403,
      "max_score": 38.91324033511728,
      "measured_at": null,
      "min_score": 16.419946190834704,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 575,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.9192387904093,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 22.96194768990786,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 329,
      "capped_draws": 36,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0422995,
        "mean": 0.027492531250000004,
        "median": 0.025548,
        "min": 0.0204145,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.21994025
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 25.333116741442588,
      "contributing_entrants": null,
      "distinct_rated_opponents": 165,
      "draws": 169,
      "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": "2026-08-05T05:05:18Z",
      "losses": 321,
      "max_score": 38.95277949062936,
      "measured_at": null,
      "min_score": 16.34618234965383,
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 329,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.4549379222972,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 22.524679946709842,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 462,
      "capped_draws": 151,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 231,
      "draws": 302,
      "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": "2026-07-31T20:22:54Z",
      "losses": 102,
      "max_score": 55.431385487557364,
      "measured_at": null,
      "min_score": 18.203309021107163,
      "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": 462,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.070285804948,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 30.680639185909847,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 260,
      "capped_draws": 7,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.3927285,
        "mean": 0.1902770625,
        "median": 0.16804049999999998,
        "min": 0.08751,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 1.914945
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 21.467686926657944,
      "contributing_entrants": null,
      "distinct_rated_opponents": 130,
      "draws": 29,
      "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": "2026-08-05T04:22:40Z",
      "losses": 332,
      "max_score": 28.85019218818374,
      "measured_at": null,
      "min_score": 15.89051825604416,
      "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": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1236.2259394503305,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "track",
      "score": 17.528292976043055,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:35:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 2074.1985502899956,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:34:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1863.9196141834548,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 79.75919518016714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:28:48Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1854.3786077597374,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 78.7550562000012,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:29:24Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1847.5791986207955,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 78.1799426050759,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 36,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 36,
      "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": "2026-08-05T02:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.4305585121388,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 72.50601879226893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 180,
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 90,
      "draws": 57,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1732.2042579092843,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 65.44532137869037,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.75915957037753,
      "unilateral_faults": 0,
      "wins": 223
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T03:42:41Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1682.8738949315364,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 62.31323923781224,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 148,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-08-03T14:42:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1684.77832627723,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 61.3843149316053,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 14.000430913942129,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 13,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T02:29:24Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.6929233650376,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.34870578570014,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1615.7106919093821,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 55.79662342229386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 144,
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 72,
      "draws": 36,
      "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": "2026-08-05T05:37:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.8022570539633,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 55.1044008888968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 27.752631729955272,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-03T13:20:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.7467039236506,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.57176981147765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 57
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 170,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 85,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-08-05T05:29:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.3675251085415,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 47.24502914491117,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 36.35967662941084,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 64,
      "draws": 60,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-05T05:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.1427938732331,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.04679801633584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 30.3772661551121,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "capped_draws": 128,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 117,
      "draws": 128,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-08-05T03:42:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.924403802806,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.20358864197766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.042462425705284,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 13,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-03T12:31:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.5108403714787,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.55026889308681,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 60,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 30,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T05:28:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.8432876524253,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.37674581224034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.102774568672196,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.3441495353725,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.24489520124794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.8654932136196,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.748929094306256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 246,
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 121,
      "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": 120,
      "max_score": null,
      "measured_at": "2026-08-05T04:13:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.2225647130356,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.87228212800732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.1524206416837046,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 9,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T05:29:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.0011543444123,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 33.26480003454013,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 41.71727501641449,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.0482856713095,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.278226848010597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 22.08718040460786,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 20,
      "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": "2026-08-05T05:37:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.7856369791552,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.54179636147906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 41.71727501641449,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 244,
      "capped_draws": 79,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "draws": 79,
      "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": 137,
      "max_score": null,
      "measured_at": "2026-08-05T04:13:36Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 243,
      "rating_method": "sequential_elo",
      "raw_elo": 1263.7243618026978,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.661903263791142,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.4392325850739818,
      "unilateral_faults": 1,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-07-31T03:20:56Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.9886564398028,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.203309021107163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1219.0922738248978,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 15.89051825604416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:35:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1191.341446805984,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 13.030258973366303,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 22.599360970396255,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 15,
      "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": "2026-08-05T03:16:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1848.6927283605112,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1762.8973316433855,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 81.91642338098146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:59Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1726.5724128111112,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 74.10763610887963,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 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": 56,
      "draws": 40,
      "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": "2026-08-04T08:44:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.0704845544929,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 73.97689904691619,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-05T01:25:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1641.8435026438312,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.16935098002528,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 66,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1605.236191959549,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.68530133471744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 72,
      "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": "2026-08-05T02:29:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.0360257430739,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.05496996375109,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 40,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-05T04:14:55Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.377695628946,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.09734496097713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 33.33174221445313,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 200,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "draws": 165,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:59Z",
      "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": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.187976281611,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.174862159682817,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.00917733558763,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-07-31T01:21:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.7218026454714,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 24.606196776104223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 92,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-03T11:50:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.958195948396,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.8282677671406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 204,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 167,
      "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": "2026-08-05T02:23:09Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.3783144201457,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.713702201359574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.523431578963063,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 315,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 152,
      "draws": 246,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-08-05T02:23:13Z",
      "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": 313,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.6823474356468,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.17228110668475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.04483610793667,
      "unilateral_faults": 2,
      "wins": 17
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 53,
      "draws": 134,
      "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": "2026-08-05T04:06:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.0237227206553,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.09827284833638,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 38.41045953184991,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.6483700277522,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.231928182356505,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.5095838835902065,
      "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": 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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:14:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.8544104693906,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.1638721019117,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-05T04:14:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.0542238659314,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.12149396001877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 22.3523064526878,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 51,
      "draws": 165,
      "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": "2026-08-04T08:44:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.8733711729035,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.83981461551393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 28.796733626714996,
      "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": 2,
      "distinct_rated_opponents": 25,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-03T08:04:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.6265901311735,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.793318043756123,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 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": 13,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-08-05T04:06:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 26,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.4301694661972,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 14.327060935420919,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "draws": 81,
      "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": "2026-08-03T14:23:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.1938068693948,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 10.34354662706081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 74,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-04T05:07:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.23350130035,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 6.649465460691646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 28.430533588759353,
      "unilateral_faults": 2,
      "wins": 2
    },
    {
      "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": 52,
      "draws": 0,
      "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": "2026-08-03T14:17:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1912.3418465864775,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 97.33599973224807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 111
    },
    {
      "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": 38,
      "draws": 44,
      "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": "2026-08-03T14:08:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.7450741307903,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 68.08895739222693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "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": 37,
      "draws": 7,
      "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": "2026-08-05T00:16:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1674.9780101817953,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 64.47438248139325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 51
    },
    {
      "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": 36,
      "draws": 16,
      "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": "2026-08-04T22:43:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.6282681640967,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.36568330922522,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 37
    },
    {
      "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": 6,
      "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": "2026-08-03T14:16:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 26,
      "rating_method": "sequential_elo",
      "raw_elo": 1606.495361338857,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 48.426383488215265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 64.99642869155205,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 89,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-03T14:17:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.5150630244484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.36721779549708,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 3,
      "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": 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": 19,
      "max_score": null,
      "measured_at": "2026-08-03T13:45:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.4871568460653,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.919362734240536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 63.08754591278003,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "draws": 65,
      "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": "2026-08-03T12:18:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.528494060152,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.26992541010253,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 29.98404749947013,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 274,
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 129,
      "draws": 101,
      "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": 98,
      "max_score": null,
      "measured_at": "2026-08-05T04:45:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.5177561237024,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.24190944943468,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.965236003466329,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 33,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T02:45:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.2301237737283,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.6743793289876,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 41.04200090392808,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 52,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 25,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T04:45:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.5338748338609,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.67859448493501,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 57.59714166026543,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 160,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 77,
      "draws": 57,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T04:45:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.742396565601,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.09417723351375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 27.960415358888525,
      "unilateral_faults": 6,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-04T03:30:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.0279417186953,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.829666021771125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 2,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T04:36:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 26,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.0723605102608,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.4038428924734,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 54.36252243246881,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "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": 13,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-04T03:25:30Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 26,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.6289635368048,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.12774530392546,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 73.70004696062244,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 15,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-03T13:44:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.1284872075441,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.22692688715613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 35,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-08-03T03:06:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.2409871410878,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.72176486319264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.22199845071155,
      "unilateral_faults": 1,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-03T14:16:49Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.4866662482673,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.49558535920104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-04T22:43:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.7892085139326,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.061882688196544,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1883.5568183188263,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 87,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:36Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1772.8326811225836,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 79.44376401396596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.3360960868538,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.68991920919109,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 53,
      "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": "2026-08-05T04:05:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1649.8433166463897,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.064818144611,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.1138216200993,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.093874217143885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 48,
      "draws": 61,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-05T06:57:15Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.8218153276666,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.8242290880386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 32.03600868187805,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.9423799806716,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.546679444120066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 70,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.800435260969,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.255041035684194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 53,
      "draws": 46,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-08-05T04:52:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.013755601416,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.62630808796079,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 32.54930561887425,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 55,
      "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": "2026-08-05T04:29:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.0415678282136,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.676324126516743,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:45Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.097654712804,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.555732530370754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 64,
      "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": "2026-07-31T02:31:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.3395528223577,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.200565710939646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 220,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 105,
      "draws": 138,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-08-05T05:05:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.168428759483,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.496322085294256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 3.713678840118715,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.62788625461,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.042469828678968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 29,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.7663160414843,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.71090838679187,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 49.43113400428921,
      "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": 2,
      "distinct_rated_opponents": 30,
      "draws": 53,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.9882412604513,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.47104312016287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 26.38386256637516,
      "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": 4,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-05T05:05:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.1431895503845,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.189651778222867,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 46.042905911570074,
      "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": 2,
      "distinct_rated_opponents": 30,
      "draws": 85,
      "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": "2026-08-05T05:05:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.9539606604203,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.115823492649717,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.806447728429966,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 84,
      "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": "2026-08-05T05:05:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.9173614142396,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.40588512859002,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 21.9692131063861,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 144,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 72,
      "draws": 143,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T06:57:05Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.582785992217,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.785677670777737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 29.851648028961442,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 27,
      "draws": 115,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T04:13:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.7829577904,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.618360953390088,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 18.7704745893458,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 218,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 105,
      "draws": 70,
      "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": 96,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:36Z",
      "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": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.466947435084,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.002828160874977,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 3.9246070243412623,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 35,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T05:04:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.5829391383131,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.855391019353213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 22.599360970396255,
      "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": 2,
      "distinct_rated_opponents": 30,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.1610541264322,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 17.326469166627668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.26622208392424,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 80,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.0958174926009,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.419946190834704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.26622208392424,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.493662395028,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 12.006801731616441,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": "2026-08-05T00:53:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 2099.7620540108987,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 94.13268706699881,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T00:52:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 2067.6605378147365,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 91.54521731701738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-03T14:57:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 2013.0080873189577,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 86.33840661001909,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.468842775200363,
      "unilateral_faults": 0,
      "wins": 140
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T01:40:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1977.5155798619357,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 84.01665989467725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T01:40:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1882.615074493054,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 76.14344213568862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T01:40:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1781.323497099848,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 67.68754926078236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:35:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1723.859615334493,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 63.045401528569364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9885453854133264,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T01:40:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.3815440244537,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 61.05007234863776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T05:05:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1717.2211615795206,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 60.18939037750328,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 35.72194732417195,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-04T22:34:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1695.9221727866338,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 59.509667167131056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.339588834282274,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:23:04Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.153408374177,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.59451105913189,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 148,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 74,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:47Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.7605219975048,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.69350786141744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 30.519493990550963,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "2026-08-05T03:58:47Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1587.0990394515595,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.723957204300376,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 244,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "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": 124,
      "max_score": null,
      "measured_at": "2026-08-05T01:40:45Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.623648139087,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.802629023107144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.4376202060078436,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-08-03T08:44:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.0681049031327,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.5644545454188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 21.79936318977655,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 394,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 191,
      "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": 204,
      "max_score": null,
      "measured_at": "2026-08-05T03:58:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 394,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.5375887832508,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.992442092413626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.32378651666526537,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-05T04:59:59Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.696720232599,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.71671953757412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 27.857940612168754,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-08-05T03:58:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.595661388488,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.197008068659926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "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": 122,
      "max_score": null,
      "measured_at": "2026-08-05T04:59:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.89287568197,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.83576466893516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.51043060464768,
      "unilateral_faults": 0,
      "wins": 112
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-08-03T10:18:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.2804128851371,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.84698418707792,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.459772198068393,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 238,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 8,
      "distinct_rated_opponents": 119,
      "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": 174,
      "max_score": null,
      "measured_at": "2026-08-05T04:59:59Z",
      "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": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.1809824903353,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.512279064156786,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 33.26244469819276,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-08-03T10:09:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.5233581127313,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.06000231216052,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.888824360518605,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 158,
      "max_score": null,
      "measured_at": "2026-08-05T00:09:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.6797930025884,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.48028584036205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.336874464495992,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 242,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 118,
      "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": "2026-08-05T02:16:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.6178552902875,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 34.450305869169036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.528142200703182,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 92,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": 104,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.6954858769009,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 26.677731076611366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.98442636283953,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1241.2401742692932,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.668950001695563,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 21.132502076248564,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 120,
      "max_score": null,
      "measured_at": "2026-08-05T05:06:20Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1248.8221416706815,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.28831645151227,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 36.34496024750244,
      "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": 2,
      "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": 95,
      "max_score": null,
      "measured_at": "2026-08-05T00:53:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1177.988284897323,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 16.34618234965383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 22.26568574800236,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-04T23:53:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 2009.1734856604521,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T02:29:19Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1905.694154233326,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 90.18024385545019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-05T01:04:28Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1885.1585395368777,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 88.3001049099167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T00:01:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1864.9721170328544,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 86.35067612265574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-04T23:53:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1862.8948429941306,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 86.15355149666183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": "2026-08-05T00:37:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1823.2710278734628,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 82.35863358446323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T01:04:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1791.117462946414,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 79.30739463261588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 28,
      "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": "2026-08-03T12:25:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1792.51834753957,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 77.86243893295662,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 25.829556801099734,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 42,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:47Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1787.873868416896,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 76.9153537911332,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "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": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": "2026-08-05T00:01:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1764.9290441113433,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 76.82222311841032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": "2026-08-05T03:09:16Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1741.4491229052383,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 74.75879788264669,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 88,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 44,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:18Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1740.0120087892494,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 72.5401989690437,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 30.30298644536222,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-08-03T13:30:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1670.792977708839,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 66.50580979104048,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.26622208392424,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-08-03T11:32:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.6573877546402,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 64.6891432709365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 24.52648327229861,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 244,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 115,
      "draws": 18,
      "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": 113,
      "max_score": null,
      "measured_at": "2026-08-05T03:09:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.872562787418,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 59.82214388179885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.4376202060078436,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-08-05T00:01:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.556641341538,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.81303259089284,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 176,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 88,
      "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": 112,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.7203640226057,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 55.56087546422818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 24.845848565914157,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "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": 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": 38,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.4105298643044,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 55.431385487557364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "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": 24,
      "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": 92,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.4845633830778,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.40171912715226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.319898871955914,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.0877615675836,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 50.38530962978662,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 33.47940711208657,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 152,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 8,
      "distinct_rated_opponents": 76,
      "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": 140,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:24Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.1954291728616,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.82771632283495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.22581938124281,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 35,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-08-05T05:13:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.582517561534,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 44.976480556909316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.09478634937246,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-08-04T23:08:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.2494860259037,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.05907181803922,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 63,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-08-04T23:17:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 63,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.5860385894107,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.91324033511728,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.966247874473638,
      "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": 2,
      "distinct_rated_opponents": 32,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-08-05T00:01:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1357.7423100535907,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 37.06130479180287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.805911392508083,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 214,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 102,
      "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": 154,
      "max_score": null,
      "measured_at": "2026-08-05T01:04:28Z",
      "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": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1283.4924627891278,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 31.187597579426182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.364069356670375,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:35:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1274.548733487929,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.85019218818374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.973505697509715,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 59,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:35:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 59,
      "rating_method": "sequential_elo",
      "raw_elo": 1269.0832415302018,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.463532438701474,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 22.234854341557245,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-08-05T00:52:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1264.4416980243168,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.91157848915521,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.70344991379835,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": "2026-08-05T04:22:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 2105.4058440588437,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:35:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 2000.6669846925447,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 90.99516388242985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:13:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1980.5083189186464,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 89.20483886963211,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:35:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1841.737030413011,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 76.93117424326455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "2026-08-05T03:42:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1804.4339757540693,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 73.56738030887553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T04:35:25Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1800.148693292092,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 73.16043333134834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 246,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:59Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1796.997875751851,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 72.91920929796846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.1611854626755758,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:43:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1748.3528347421668,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 68.58671985118539,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:43:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.5864634999832,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 58.3941253924312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 178,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 89,
      "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": 113,
      "max_score": null,
      "measured_at": "2026-08-05T04:31:02Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.509245658041,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 57.021020326201075,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 24.313035635484873,
      "unilateral_faults": 0,
      "wins": 163
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1611.1347947383947,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 56.45100183671994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.617825470805693,
      "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": 2,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-04T22:51:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.2275642237973,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 55.753611595590186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 21.79936318977655,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "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": 110,
      "max_score": null,
      "measured_at": "2026-08-05T03:42:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.6677941963164,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.873388733034076,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9885453854133264,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 154,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 77,
      "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": "2026-08-05T06:56:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.3503322080414,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 54.395254355004845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 27.321327784310522,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "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": 101,
      "max_score": null,
      "measured_at": "2026-08-05T04:30:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1587.5380517863227,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.130070940092246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.863085897764936,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 378,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 180,
      "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": 183,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 378,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.489463921882,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 53.01864952960553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.620576779027561,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 250,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "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": 134,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:03Z",
      "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": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.3211884250354,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 51.56133301083614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.4376202060078436,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "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": 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": "2026-08-03T15:11:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.7262387953551,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.82745014205055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.831799173767003,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 65,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-08-05T04:31:02Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 65,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.2585103323468,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 43.412038961161755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 30.542286733757642,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 60,
      "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": 100,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.8991729354007,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.53688282449636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 31.160696943995934,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 260,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 8,
      "distinct_rated_opponents": 130,
      "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": 230,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.3414112535602,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 41.07624386646105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 32.27158650165324,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.5051547512048,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 40.61113499633033,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-08-05T02:09:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.3878157010372,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 38.95277949062936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 18.466769200052298,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-08-05T01:17:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.2791878007524,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 36.45926297584206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.926543555546573,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 73,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T03:50:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 73,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.6689853530577,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 30.214369480459318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.80894910339042,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1315.0784435685223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.228737245304664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 27.76799953545848,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-08-05T04:12:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.9786118237457,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 27.74104627006085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.007326216468247,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": 98,
      "max_score": null,
      "measured_at": "2026-08-05T04:22:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1210.0225762192022,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.461087260708307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.850427786204904,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-05T04:44:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 2055.9331893482595,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 222,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-05T04:52:03Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1829.26608314685,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 74.0721732581313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 3.4969716034024056,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.1758610356108,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 70.00316477029536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 222,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 111,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-08-05T03:58:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1796.9439417067679,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 68.96755045489611,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.51136721509174,
      "unilateral_faults": 0,
      "wins": 291
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T04:44:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1774.4726146237526,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 68.19729379593623,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 22,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T04:23:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.3119824922603,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.93948176668485,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1606.092096601223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 49.12291169798428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.2791154741321,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 46.74935663358592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 14.239212718233443,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 31,
      "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": "2026-08-05T04:44:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.607560959858,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.98316602186302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 386,
      "capped_draws": 169,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 187,
      "draws": 169,
      "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": 91,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 386,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.4716211595342,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 45.330135882794195,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.2967902623622957,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 52,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-03T13:54:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.1308178470354,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 42.48130098619828,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 52.475044864937615,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 264,
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 127,
      "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": 93,
      "max_score": null,
      "measured_at": "2026-08-05T04:52:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.9101728693004,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 39.43308067787763,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.3089127354028465,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 376,
      "capped_draws": 137,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 183,
      "draws": 137,
      "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": 142,
      "max_score": null,
      "measured_at": "2026-08-05T04:51:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 376,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.8881549864773,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.71113006655985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.7682804277891364,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 142,
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 71,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.638154159525,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 35.01219161214689,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.40895509928201,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 222,
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 111,
      "draws": 104,
      "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": 95,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.2886959682157,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 32.48570871237849,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 40.64520801091697,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 71,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T04:23:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.7661257245363,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 29.014574794367363,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 95,
      "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": "2026-08-05T04:43:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.1134240521621,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.601263953234557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "draws": 31,
      "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": "2026-08-03T12:45:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.8212261015778,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 28.081470669645384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.237183532345085,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 92,
      "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": "2026-07-31T02:43:26Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.890887252805,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.961738933840852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 86,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T04:23:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.1496435571894,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 25.37839192404362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 36,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "draws": 85,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-04T23:45:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.229001478985,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.61720886725491,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 14.836607386351783,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T00:38:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.141283069378,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 23.049881684857795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.747146215609725,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 152,
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 76,
      "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": 71,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.232126813642,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 22.15352632879835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.767357465638472,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_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": "2026-08-05T02:53:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1381.5144800797461,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.756531763359927,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 22.007943739905976,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 36,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "draws": 85,
      "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": "2026-08-05T02:15:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.8979860686834,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 21.497204299638256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.85345304153558,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 37,
      "draws": 62,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T04:44:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.4925532767802,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 20.92911913796267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 27.375226195907118,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-08-05T04:22:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.5846777749914,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 19.935559087203618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "draws": 62,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T04:51:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.6468603917838,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 18.58079185799611,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 24.772182566181264,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "draws": 74,
      "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": "2026-08-05T03:58:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.4253612380444,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260806-59b3356f5989",
      "row_kind": "game",
      "score": 12.88406623711618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v10",
      "snapshot_id": "20260806_094024",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 21.20639198938312,
      "unilateral_faults": 0,
      "wins": 0
    }
  ],
  "schema_version": 9,
  "snapshot_id": "20260806_094024",
  "suite_line_id": "gamebench2",
  "suite_version": "2-known8-r3"
}